© 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. 20-GEMMASCOPE-RES-131K
    6. 67656
    Prev
    Next
    INDEX
    Explanations

    technical terms and elements specific to programming and server configurations

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

    key-value pairs

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    EndContext
    -0.53
    AndEndTag
    -0.52
    richTextPanel
    -0.47
    itology
    -0.45
    CGSize
    -0.45
    ChildScrollView
    -0.44
    replies
    -0.42
    inerario
    -0.42
     Chronology
    -0.41
     CGSize
    -0.40
    POSITIVE LOGITS
    
    0.37
    MLLoader
    0.37
    principalColumn
    0.36
    ">—
    0.36
    RetentionPolicy
    0.36
     externi
    0.35
    thenReturn
    0.35
    MigrationBuilder
    0.35
    Geplaatst
    0.35
     EconPapers
    0.35
    Activations Density 0.110%

    No Known Activations