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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 17-GEMMASCOPE-RES-16K
    6. 5140
    Prev
    Next
    INDEX
    Explanations

    special characters and whitespace formatting in code or text

    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
     Wheeler
    -0.57
    Collegamenti
    -0.57
     Ayres
    -0.55
     --
    -0.53
    dataIndex
    -0.53
     “
    -0.52
     V
    -0.52
    ,
    -0.49
     –
    -0.49
     R
    -0.48
    POSITIVE LOGITS
     itſelf
    0.71
     Swedes
    0.70
    utnik
    0.70
     surla
    0.69
     Efq
    0.68
     myſelf
    0.67
     themſelves
    0.66
    ViewFeatures
    0.66
    )».
    0.63
     Theſe
    0.63
    Activations Density 0.005%

    No Known Activations