© 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. 28016
    Prev
    Next
    INDEX
    Explanations

    references to specific characters and coding functions

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

    Terminator cycle, ServerSocket timeout, Yoda spit

    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
     Rauch
    -0.41
     webdriver
    -0.38
    ietf
    -0.36
     sû
    -0.35
    Referințe
    -0.34
     campana
    -0.34
     vysok
    -0.34
     sabbia
    -0.34
    arXiv
    -0.34
     sayap
    -0.33
    POSITIVE LOGITS
     Zidane
    0.96
     Federer
    0.92
    Terminator
    0.85
     Terminator
    0.84
    PageInfo
    0.84
     Abp
    0.84
     Nadal
    0.83
     ModelExpression
    0.80
     setw
    0.79
     Obi
    0.76
    Activations Density 0.001%

    No Known Activations