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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 15026
    Prev
    Next
    INDEX
    Explanations

    specific terms and phrases related to structured data or variables in code and analytical contexts

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

    Followed by punctuation or brackets

    np_acts-logits-general · gemini-2.0-flash

    state, boxes, $

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    IRUS
    -0.80
    !...
    -0.73
    UserScript
    -0.72
     !...
    -0.70
    iric
    -0.66
    thâu
    -0.65
    ✭✭
    -0.65
     nordic
    -0.65
     للمعارف
    -0.64
    (;;)
    -0.64
    POSITIVE LOGITS
    ),
    1.02
    )
    0.94
     were
    0.88
    ,
    0.84
    ?
    0.82
    )?
    0.82
     are
    0.82
     will
    0.80
     was
    0.80
    ?");
    0.76
    Activations Density 3.254%

    No Known Activations