© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 31-GEMMASCOPE-RES-16K
    6. 15735
    Prev
    Next
    INDEX
    Explanations

    phrases related to unfamiliar experiences or knowledge

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    phrases expressing unfamiliarity or lack of knowledge about something.

    oai_token-act-pair · claude-4-5-haikuTriggered by @emiglarou
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_31/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     setia
    -0.36
    Hochspringen
    -0.35
    ContentAsync
    -0.35
    BeginContext
    -0.34
    点此举报
    -0.34
    ništvo
    -0.33
     ufficiale
    -0.33
    δι
    -0.33
     privée
    -0.33
    ApiModelProperty
    -0.32
    POSITIVE LOGITS
     heard
    2.34
     hear
    1.92
     hears
    1.90
     hearing
    1.88
    heard
    1.87
    Heard
    1.63
     Heard
    1.56
    hearing
    1.55
     Hearing
    1.53
    听说
    1.48
    Activations Density 0.432%

    No Known Activations