© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 12-GEMMASCOPE-RES-16K
    11. 3983
    Prev
    Next
    INDEX
    Explanations

    instances of uncertainty or questioning statements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    The neuron detects tokens that occur at the start of sentences or answer lines — i.e., sentence-initial/discourse-starter tokens.

    oai_token-act-pair · gpt-5-miniTriggered by @phamvanluong2003

    Q&A-style answer sections, especially the “A:” label and the start of an answer response.

    oai_token-act-pair · gpt-5Triggered by @areeb0102

    answers or responses in a Q&A format.

    oai_token-act-pair · deepseek-r1Triggered by @areeb0102

    the beginning of answer sections in Q&A formatted text.

    oai_token-act-pair · claude-4-5-haikuTriggered by @areeb0102
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    endphp
    -1.07
    enumi
    -0.92
     كومونز
    -0.80
     насељу
    -0.80
     '\\;'
    -0.78
    AnimationsModule
    -0.77
     resourceCulture
    -0.76
    pédie
    -0.74
    ]")]
    -0.74
    posedge
    -0.72
    POSITIVE LOGITS
    Absolutely
    0.49
    Exactly
    0.48
    Definitely
    0.45
    You
    0.45
     păr
    0.43
     jūsų
    0.41
     Exactly
    0.41
     felizes
    0.41
    Set
    0.40
     Absolutely
    0.40
    Activations Density 0.267%

    No Known Activations