© 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. 31-GEMMASCOPE-RES-16K
    11. 8009
    Prev
    Next
    INDEX
    Explanations

    specific organization names, contact details, and references to addresses or locations

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

    contact information and addresses in documents.

    oai_token-act-pair · claude-4-5-haikuTriggered by @emiglarou
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_31/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    GenerationType
    -0.41
    новништво
    -0.39
     مشين
    -0.39
    Explicación
    -0.39
    CreateModel
    -0.39
    🗳
    -0.38
     embarrassed
    -0.38
    Hintergrund
    -0.37
    +#+#
    -0.36
     embarrassing
    -0.36
    POSITIVE LOGITS
     www
    1.23
    www
    1.06
     website
    1.03
     Website
    0.97
     email
    0.95
     Phone
    0.94
     phone
    0.93
     Email
    0.90
    Website
    0.90
     contact
    0.87
    Activations Density 0.195%

    No Known Activations