© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B-IT
    7. Residual Stream - 131k
    9. 9-GEMMASCOPE-RES-131K
    11. 29913
    Prev
    Next
    INDEX
    Explanations

    code-related elements, particularly focusing on requests and responses within a programming context

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

    programming method calls and syntax

    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
    Personendaten
    -0.69
    AutoScaleMode
    -0.60
    complexContent
    -0.58
     BoxFit
    -0.56
    tangentMode
    -0.53
    VersionUID
    -0.52
     pinulongan
    -0.49
     Normdatei
    -0.46
     autorytatywna
    -0.45
    sidemargin
    -0.45
    POSITIVE LOGITS
    toISOString
    0.42
     下午
    0.40
     geçir
    0.37
    blech
    0.37
     Auss
    0.37
    SourceChecksum
    0.37
    netinet
    0.35
     Polskiej
    0.35
     peč
    0.35
    contain
    0.35
    Activations Density 0.501%

    No Known Activations