© 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. 7-GEMMASCOPE-RES-16K
    11. 15572
    Prev
    Next
    INDEX
    Explanations

    references to graphs, diagrams, or structured representations of information

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 7-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_7/width_16k/average_l0_92
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Hook Layer
    7
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    TagMode
    -0.69
    parsedMessage
    -0.66
     arşivlendi
    -0.65
     فريبيس
    -0.63
     لينك
    -0.61
    ftagPool
    -0.60
     مرئيه
    -0.55
    ScopeManager
    -0.54
    QMetaType
    -0.54
     ModelExpression
    -0.54
    POSITIVE LOGITS
    SerializedName
    0.36
    enfance
    0.32
    glTranslatef
    0.32
    BASEPATH
    0.32
    Handlung
    0.31
     Außerdem
    0.31
    Tikang
    0.28
    ordinateur
    0.28
    Readers
    0.28
    ("(
    0.28
    Activations Density 1.648%

    No Known Activations