© 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. 9-GEMMASCOPE-RES-131K
    6. 55585
    Prev
    Next
    INDEX
    Explanations

    references to academic institutions and associated personnel

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

    universities

    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
    IsMutable
    -0.37
    Toponymie
    -0.32
     wä
    -0.31
     náv
    -0.30
    AISSEE
    -0.29
     sarung
    -0.29
    blurRadius
    -0.29
     Auff
    -0.29
     lemn
    -0.29
    StateList
    -0.29
    POSITIVE LOGITS
     propOrder
    0.55
    scriptcase
    0.53
    rrggbb
    0.50
    ⓧ
    0.50
    Southampton
    0.50
     sociologists
    0.50
    Nottingham
    0.50
     DTS
    0.50
     UCL
    0.48
     Nottingham
    0.47
    Activations Density 0.023%

    No Known Activations