© 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. 3-GEMMASCOPE-RES-16K
    11. 1137
    Prev
    Next
    INDEX
    Explanations

    terms related to family lineage and ancestry

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    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
    -0.76
    IsContent
    -0.55
    medriver
    -0.54
    InSection
    -0.52
    uttosto
    -0.51
     Pearls
    -0.51
    enseur
    -0.50
    rinfo
    -0.50
    omości
    -0.49
     חיצוניים
    -0.49
    POSITIVE LOGITS
     Roskov
    0.70
    adpleegd
    0.62
    HttpStatusCode
    0.58
     بتاريخ
    0.56
     HasFactory
    0.54
    disambiguation
    0.54
     assust
    0.53
    IContainer
    0.53
     đo
    0.53
    CODES
    0.53
    Activations Density 0.331%

    No Known Activations