© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 131k
    5. 31-GEMMASCOPE-RES-131K
    6. 12667
    Prev
    Next
    INDEX
    Explanations

    references to manufacturers and their protocols in scientific contexts

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

    manufacturer's instructions or protocols

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 31-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_31/width_131k/average_l0_109
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    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
     Choice
    -0.32
     gef
    -0.31
     post
    -0.30
     Bar
    -0.30
    azo
    -0.29
    teis
    -0.27
     sor
    -0.27
     Freelance
    -0.27
     ber
    -0.27
     Post
    -0.26
    POSITIVE LOGITS
     recommended
    1.41
     recommendations
    1.36
    recommended
    1.21
     manufacturer
    1.21
     recommendation
    1.19
     recommends
    1.18
     instructions
    1.16
     recommandations
    1.16
     Recommendations
    1.11
    recommendations
    1.11
    Activations Density 0.060%

    No Known Activations