© 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. 40-GEMMASCOPE-RES-16K
    6. 5263
    Prev
    Next
    INDEX
    Explanations

    structural elements and formatting tags in HTML

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 40-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_40/width_16k/average_l0_125
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.40.hook_resid_post
    Hook Layer
    40
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Compos
    -0.78
    CYCLE
    -0.75
    Cascade
    -0.75
    Kom
    -0.74
    Kons
    -0.73
    Commit
    -0.73
    COMPOS
    -0.73
    Comprom
    -0.73
    Cycle
    -0.73
    Constitu
    -0.73
    POSITIVE LOGITS
     с
    0.47
     c
    0.40
    𝕐
    0.37
     ç
    0.36
    istoitu
    0.35
    ค
    0.35
    Ос
    0.32
    сс
    0.32
     הק
    0.32
    AndView
    0.31
    Activations Density 4.010%

    No Known Activations