© 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
    7. Residual Stream - 16k
    9. 12-GEMMASCOPE-RES-16K
    11. 3075
    Prev
    Next
    INDEX
    Explanations

    method calls related to retrieving or handling string resources

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 12-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_12/width_16k/average_l0_130
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    脚注の使い方
    -0.88
    )_/¯
    -0.66
    migrationBuilder
    -0.64
    bootstrapcdn
    -0.64
    点此举报
    -0.61
    adaptiveStyles
    -0.61
     ſoll
    -0.60
    ௃
    -0.60
     disambiguazione
    -0.60
    <unused70>
    -0.58
    POSITIVE LOGITS
    getString
    1.59
     getString
    1.19
    setString
    1.01
    GetString
    0.95
    getStringExtra
    0.94
    getInt
    0.83
    putString
    0.81
    getBoolean
    0.79
    getJSONObject
    0.65
    getFloat
    0.63
    Activations Density 0.051%

    No Known Activations