© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 2-GEMMASCOPE-RES-16K
    11. 12892
    Prev
    Next
    INDEX
    Explanations

    phrases that describe the purpose or function of objects or systems

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_2/width_16k/average_l0_67
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ModelExpression
    -0.59
     snippetHide
    -0.53
     linkovi
    -0.52
     للاسماء
    -0.52
    windowFixed
    -0.52
     initComponents
    -0.52
    protoimpl
    -0.49
    ソッド
    -0.47
    Autoritní
    -0.46
    StoreMessageInfo
    -0.46
    POSITIVE LOGITS
     calculated
    0.75
     designed
    0.73
     computed
    0.73
     estimated
    0.63
    designed
    0.60
     Designed
    0.59
    calculated
    0.58
    Designed
    0.57
     Calculated
    0.55
     advised
    0.55
    Activations Density 0.078%

    No Known Activations