© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 12-GEMMASCOPE-RES-16K
    6. 5115
    Prev
    Next
    INDEX
    Explanations

    scientific and technical terminology related to data and measurements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 12-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_12/width_16k/average_l0_130
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     pleaſure
    -0.61
    protoimpl
    -0.52
     ſtate
    -0.52
     snippetHide
    -0.49
     Meksiku
    -0.47
    Rüyada
    -0.45
     houſe
    -0.45
     ſmall
    -0.44
     myſelf
    -0.44
    TypedDataSet
    -0.43
    POSITIVE LOGITS
    phanumeric
    0.52
    //
    0.49
    IsNullOrEmpty
    0.48
    enderror
    0.47
    rrggbb
    0.46
    存于互联网档案馆
    0.46
    FDRE
    0.46
    keyValue
    0.46
    秋冬
    0.42
    fromLTRB
    0.42
    Activations Density 1.258%

    No Known Activations