Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 16-GEMMASCOPE-RES-16K
    6. 16026
    Prev
    Next
    INDEX
    Explanations

    references to historical events and their interpretations

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

    a starting point or origin

    np_acts-logits-general · gemini-2.0-flash

    from the beginning, always

    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
     Lordships
    -0.62
    expandindo
    -0.58
    RenderAtEndOf
    -0.58
    EndContext
    -0.57
     currently
    -0.49
    *}$
    -0.49
    LookAnd
    -0.49
    corrência
    -0.48
    hdl
    -0.48
    ksikon
    -0.47
    POSITIVE LOGITS
    最初から
    1.45
     dès
    1.04
    一开始
    0.99
    Dès
    0.99
    Always
    0.96
     Always
    0.92
    一開始
    0.90
    начально
    0.84
     Dès
    0.83
     never
    0.82
    Activations Density 0.336%

    No Known Activations