© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 1-GEMMASCOPE-RES-16K
    6. 3740
    Prev
    Next
    INDEX
    Explanations

    declarations of data types and structures in programming code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 1-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_1/width_16k/average_l0_69
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.1.hook_resid_post
    Hook Layer
    1
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Rücks
    -0.41
     INSEE
    -0.39
     huom
    -0.39
    TemporalType
    -0.38
     sexe
    -0.38
    嘧
    -0.37
     HasFactory
    -0.37
    vician
    -0.36
    ніципалі
    -0.35
    DeleteCommand
    -0.35
    POSITIVE LOGITS
     EventArgs
    0.75
     Authentication
    0.60
    Authentication
    0.59
     للمعارف
    0.58
    下载附件
    0.58
    #+#
    0.57
    typedef
    0.57
     trustees
    0.56
     authentication
    0.55
     authenticate
    0.55
    Activations Density 0.410%

    No Known Activations