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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 25-GEMMASCOPE-RES-16K
    11. 15889
    Prev
    Next
    INDEX
    Explanations

    specific time references and scoring events in a sports context

    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
    İstinadlar
    -0.65
     ModelExpression
    -0.65
    rings
    -0.61
    onaceous
    -0.58
    PhysRevLett
    -0.58
     jsPsych
    -0.58
     inoxydable
    -0.56
    thâu
    -0.55
     dependents
    -0.55
    houding
    -0.54
    POSITIVE LOGITS
     frame
    0.93
     period
    0.91
    frame
    0.83
     stanza
    0.80
     half
    0.76
     Period
    0.73
     frames
    0.73
     Frame
    0.72
    period
    0.72
     periods
    0.71
    Activations Density 0.236%

    No Known Activations