© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 23-GEMMASCOPE-RES-16K
    11. 9654
    Prev
    Next
    INDEX
    Explanations

    instances of the word "match" and its variations indicating comparisons or connections

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 23-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_23/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.hook_resid_post
    Hook Layer
    23
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     newUser
    -0.63
    errHandler
    -0.52
     Menon
    -0.50
     Fonseca
    -0.50
    anthene
    -0.48
    newUser
    -0.48
     DHCP
    -0.47
    Portale
    -0.46
     Herv
    -0.46
    OrWhiteSpace
    -0.46
    POSITIVE LOGITS
     Match
    0.97
     match
    0.91
    Match
    0.91
     MATCH
    0.91
    match
    0.88
    MATCH
    0.85
     Matches
    0.77
     matches
    0.73
     Fit
    0.73
     fit
    0.71
    Activations Density 0.162%

    No Known Activations