© 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. 68470
    Prev
    Next
    INDEX
    Explanations

    references to national issues and entities

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

    national events and contexts

    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
    ագրություններ
    -0.66
     noDo
    -0.61
    ClCompile
    -0.59
    ChildScrollView
    -0.55
    MemoryWarning
    -0.54
    multicolumn
    -0.52
    enumi
    -0.52
    WebElementEntity
    -0.52
    <0xDA>
    -0.50
    edback
    -0.49
    POSITIVE LOGITS
     national
    1.78
    national
    1.38
     nacional
    1.26
     nationwide
    1.19
     nationally
    1.18
     nationale
    1.14
     nasional
    1.10
     национа
    1.10
     nationaux
    1.08
     nationales
    1.06
    Activations Density 0.015%

    No Known Activations