© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 10-GEMMASCOPE-RES-16K
    6. 12569
    Prev
    Next
    INDEX
    Explanations

    phrases that indicate the act of providing assistance or resources

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_10/width_16k/average_l0_113
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     tatuagem
    -0.52
    RenderAtEndOf
    -0.48
    ionario
    -0.47
    DatabaseError
    -0.47
     userSchema
    -0.46
     reação
    -0.44
    mouseup
    -0.44
     appunto
    -0.44
    ヤバ
    -0.43
    ToMany
    -0.42
    POSITIVE LOGITS
     Provide
    1.52
     provide
    1.44
    Provide
    1.41
    provide
    1.41
     provided
    1.41
     Providing
    1.36
    提供
    1.30
     providing
    1.29
     Provided
    1.28
    provided
    1.27
    Activations Density 0.162%

    No Known Activations