© 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. 9-GEMMASCOPE-RES-16K
    6. 9954
    Prev
    Next
    INDEX
    Explanations

    organization and management of wiring systems

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

    electrical components and wiring-related terminology in technical documents.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_9/width_16k/average_l0_100
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    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
    Carriera
    -0.35
    ModelSerializer
    -0.35
    แ
    -0.33
    branding
    -0.32
    对
    -0.32
     Brink
    -0.32
    artifactId
    -0.32
    栓
    -0.30
    insegna
    -0.30
    IBOutlet
    -0.30
    POSITIVE LOGITS
     Eſ
    0.69
     raiſ
    0.68
     myſelf
    0.67
     Anſ
    0.65
     itſelf
    0.65
     ſch
    0.63
     queſta
    0.62
    HtmlAttribute
    0.61
     miniaturka
    0.61
     ſta
    0.60
    Activations Density 0.253%

    No Known Activations