© 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. 22-GEMMASCOPE-RES-16K
    6. 14501
    Prev
    Next
    INDEX
    Explanations

    descriptions of mechanical components and their features

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_22/width_16k/average_l0_123
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    atzung
    -0.33
    colorbar
    -0.29
     altri
    -0.29
     Dual
    -0.28
     dual
    -0.28
     description
    -0.27
     dubbel
    -0.27
     rédaction
    -0.27
    Dual
    -0.26
    เอง
    -0.26
    POSITIVE LOGITS
     autorytatywna
    0.80
    DockStyle
    0.80
    awtextra
    0.77
    complexContent
    0.74
     surla
    0.73
     defaultstate
    0.71
    +#+#
    0.69
    دانشنامهٔ
    0.69
    حوالہ
    0.65
    adaptiveStyles
    0.61
    Activations Density 0.550%

    No Known Activations