© 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. 121447
    Prev
    Next
    INDEX
    Explanations

    technical specifications and standards related to materials and components

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

    specifications and standards

    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
    RegressionTest
    -0.61
    OCCURRED
    -0.50
     '\\;'
    -0.47
    __":
    
    -0.46
     Infórmanos
    -0.45
    Cyfarwyddwr
    -0.45
    曖昧さ回避
    -0.45
     Sensi
    -0.45
     lizenzfreies
    -0.44
    qrstuvwxyz
    -0.44
    POSITIVE LOGITS
     standards
    0.59
     Specification
    0.52
     specifications
    0.50
     specification
    0.50
     Specifications
    0.48
     standard
    0.48
    standards
    0.48
     Standards
    0.48
     STANDARDS
    0.47
    migrationBuilder
    0.46
    Activations Density 0.030%

    No Known Activations