© 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. 5-GEMMASCOPE-RES-16K
    11. 6157
    Prev
    Next
    INDEX
    Explanations

    terms related to dates, timelines, or events in a chronological context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ftill
    -0.56
    findpost
    -0.55
    saraba
    -0.55
    deus
    -0.54
     itſelf
    -0.52
     againſt
    -0.51
     affari
    -0.51
     SqlDbType
    -0.51
    ahal
    -0.51
    AsUp
    -0.49
    POSITIVE LOGITS
     dAtA
    0.58
    endphp
    0.56
    ormais
    0.56
     Effekt
    0.54
    ///</
    0.53
    hoben
    0.52
    日起
    0.52
    }-${
    0.52
     deste
    0.52
    คัญ
    0.51
    Activations Density 0.264%

    No Known Activations