© 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. 907
    Prev
    Next
    INDEX
    Explanations

    technical terms and identifiers related to authentication and logging processes

    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
    bibfield
    -0.54
     gynhyrchwyd
    -0.52
    bibinfo
    -0.47
    arangay
    -0.45
    cinema
    -0.45
    citenamefont
    -0.43
    BagConstraints
    -0.43
    ImageContext
    -0.43
    turismo
    -0.43
    utives
    -0.43
    POSITIVE LOGITS
    also
    0.79
    where
    0.74
    not
    0.72
    only
    0.72
    just
    0.72
    before
    0.71
    why
    0.68
    here
    0.68
    Then
    0.68
    though
    0.68
    Activations Density 1.415%

    No Known Activations