© 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-2-9B
    7. Residual Stream - 16k
    9. 35-GEMMASCOPE-RES-16K
    11. 12666
    Prev
    Next
    INDEX
    Explanations

    function declarations and their parameters in code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 35-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_35/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.35.hook_resid_post
    Hook Layer
    35
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     oprot
    -0.47
    letics
    -0.46
    ipeline
    -0.45
    addAll
    -0.45
     newNode
    -0.44
     GetAll
    -0.43
    تقاوى
    -0.43
    addCell
    -0.42
    newUser
    -0.41
    ForAll
    -0.41
    POSITIVE LOGITS
    ById
    1.09
    ByID
    0.87
     findById
    0.80
    byId
    0.77
    findById
    0.75
     getById
    0.73
    getById
    0.73
     by
    0.66
    ByPrimaryKey
    0.65
    ViewById
    0.64
    Activations Density 0.212%

    No Known Activations