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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 16-GEMMASCOPE-RES-16K
    11. 8638
    Prev
    Next
    INDEX
    Explanations

    elements related to decision-making and conditions in programming contexts

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

    a binary choice or alternatives

    np_acts-logits-general · gemini-2.0-flash

    choice or alternative

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    enumi
    -0.68
    Jeografia
    -0.60
    DeleteBehavior
    -0.53
    __);
    -0.51
     PLWABN
    -0.51
    ämään
    -0.51
    rás
    -0.49
    }\]
    -0.49
    gadier
    -0.48
     naselje
    -0.48
    POSITIVE LOGITS
     versus
    1.10
     vs
    1.06
    それとも
    0.97
     tantôt
    0.85
     whether
    0.84
     or
    0.83
     Versus
    0.83
    versus
    0.81
     WHETHER
    0.80
     или
    0.80
    Activations Density 0.626%

    No Known Activations