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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 17-GEMMASCOPE-RES-16K
    6. 6517
    Prev
    Next
    INDEX
    Explanations

    references to scientific collaborations and research groups

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 17-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_17/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.17.hook_resid_post
    Hook Layer
    17
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ^(@)
    -1.05
    awtextra
    -0.98
     snippetHide
    -0.97
    sizeCache
    -0.94
    $")
    -0.90
    rungsseite
    -0.90
    %");
    -0.86
    ]='\
    -0.84
    ロウィン
    -0.84
    .[/
    -0.84
    POSITIVE LOGITS
     et
    0.66
     and
    0.66
     &
    0.63
    ,
    0.54
    with
    0.44
    .
    0.43
    ;
    0.43
    .,
    0.42
     with
    0.42
    G
    0.42
    Activations Density 0.439%

    No Known Activations