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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 31-GEMMASCOPE-RES-16K
    11. 8786
    Prev
    Next
    INDEX
    Explanations

    mentions of a specific gene or protein associated with cellular activity

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

    abbreviations and technical codes that appear in academic citations and scientific notation (such as "Ap.", "AP-1", "APPDIR").

    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
    contentLoaded
    -0.50
     piele
    -0.40
    rungsseite
    -0.40
    adaptiveStyles
    -0.40
     prêtres
    -0.39
     Grecs
    -0.38
     Verhältnisse
    -0.38
     Stärke
    -0.37
     fleste
    -0.37
    tvguidetime
    -0.37
    POSITIVE LOGITS
     Ap
    0.80
     AP
    0.71
     ap
    0.66
     Aps
    0.66
     Aper
    0.64
    Ap
    0.62
     APR
    0.59
     Apri
    0.57
     aps
    0.54
     APE
    0.54
    Activations Density 0.388%

    No Known Activations