© 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. 107791
    Prev
    Next
    INDEX
    Explanations

    LaTeX commands and syntax related to document formatting

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

    LaTeX footnote marker

    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
     di
    -0.32
    แดง
    -0.29
     part
    -0.29
     ver
    -0.28
     to
    -0.26
     entries
    -0.26
     protected
    -0.26
     partly
    -0.26
     conosco
    -0.25
    phorbia
    -0.25
    POSITIVE LOGITS
    oredCriteria
    0.81
    AndEndTag
    0.78
    OGND
    0.75
    StructEnd
    0.74
    帖最后由
    0.72
     ModelExpression
    0.71
    Personendaten
    0.71
    adaptiveStyles
    0.71
     resourceCulture
    0.70
    Aholisi
    0.70
    Activations Density 0.004%

    No Known Activations