© 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-IT
    7. Residual Stream - 131k
    9. 9-GEMMASCOPE-RES-131K
    11. 121239
    Prev
    Next
    INDEX
    Explanations

    questions or statements that seek an explanation or rationale behind actions or events

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

    explaining the reason why

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_131k/average_l0_121
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    
    -0.69
    IUrlHelper
    -0.68
     cherchés
    -0.63
     Signalez
    -0.62
    WithIOException
    -0.61
    WebServlet
    -0.61
    AutoScaleMode
    -0.53
     Infórmanos
    -0.52
     beginnetje
    -0.52
     оригіналу
    -0.50
    POSITIVE LOGITS
     why
    0.57
     how
    0.52
     that
    0.46
     üzere
    0.44
    arden
    0.44
     every
    0.44
     who
    0.44
     Why
    0.43
     Franken
    0.42
    Why
    0.42
    Activations Density 0.007%

    No Known Activations