Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 9052
    Prev
    Next
    INDEX
    Explanations

    references to electronic devices and semiconductor technologies

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

    author initials or abbreviated names in academic citations.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi

    author names and initials in academic citations.

    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
    Tembelea
    -0.60
     nahilalakip
    -0.53
     للمعارف
    -0.49
     orgánico
    -0.48
     AssemblyCulture
    -0.46
     antidesliz
    -0.46
    忑
    -0.45
    исленность
    -0.45
     anhänger
    -0.45
     queſta
    -0.45
    POSITIVE LOGITS
     EoL
    0.57
    E
    0.55
    FetchType
    0.46
    matta
    0.46
     Euch
    0.45
    EA
    0.45
     EA
    0.44
     E
    0.44
     Eud
    0.43
    ejs
    0.43
    Activations Density 2.403%

    No Known Activations