© 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-2-2B
    4. Residual Stream - 16k
    5. 25-GEMMASCOPE-RES-16K
    6. 4646
    Prev
    Next
    INDEX
    Explanations

    programming-related syntax and structure

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.hook_resid_post
    Hook Layer
    25
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     jsPsych
    -0.64
     Schwert
    -0.56
     consultato
    -0.54
    losseum
    -0.53
    windowFixed
    -0.53
    予備
    -0.50
    ()];
    -0.48
     Runde
    -0.47
    gnore
    -0.46
     Objection
    -0.45
    POSITIVE LOGITS
    namespace
    1.33
    using
    1.08
     namespace
    1.03
     using
    0.86
    DockStyle
    0.71
    internal
    0.67
    Namespace
    0.66
     Namespace
    0.66
    partial
    0.66
     USING
    0.63
    Activations Density 0.095%

    No Known Activations