© 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. 20126
    Prev
    Next
    INDEX
    Explanations

    phrases or terms associated with programming constructs and errors

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

    programming method calls

    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
    lru
    -0.30
     Redding
    -0.28
     marginal
    -0.28
    DataTo
    -0.27
     well
    -0.27
     Tourism
    -0.26
     averted
    -0.26
    Auth
    -0.25
     refugee
    -0.25
     sotto
    -0.25
    POSITIVE LOGITS
     AssemblyTitle
    2.81
    setVerticalGroup
    1.33
     AssemblyProduct
    1.29
    pulumi
    1.23
     ModelExpression
    1.18
    aspectj
    1.11
     NSCoder
    1.11
    XmlType
    1.11
    epam
    1.09
    ISupport
    1.07
    Activations Density 0.001%

    No Known Activations