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

    Neuronpedia

    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. 52198
    Prev
    Next
    INDEX
    Explanations

    references to identifiers and metadata in code, particularly focusing on names, titles, and attributes

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

    code identifiers or names

    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
     Succ
    -0.47
    Succ
    -0.40
     succ
    -0.40
     ourselves
    -0.36
     Gli
    -0.36
    大军
    -0.36
     Per
    -0.36
     survi
    -0.35
     Suc
    -0.35
     ngo
    -0.35
    POSITIVE LOGITS
    adaptiveStyles
    0.63
    Personendaten
    0.60
    tonode
    0.58
    complexContent
    0.58
    tagHelperRunner
    0.57
    rawDesc
    0.57
    şört
    0.57
    expandindo
    0.56
    ArgsConstructor
    0.52
    GraphicsUnit
    0.47
    Activations Density 0.033%

    No Known Activations