© 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. 37-GEMMASCOPE-RES-16K
    11. 4200
    Prev
    Next
    INDEX
    Explanations

    phrases related to roles and role-playing activities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 37-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_37/width_16k/average_l0_124
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.37.hook_resid_post
    Hook Layer
    37
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    SequentialGroup
    -0.48
    ViewImports
    -0.44
    -------------</
    -0.44
    Sklici
    -0.41
    __":
    -0.40
    ancio
    -0.39
    velles
    -0.39
    もしれない
    -0.39
    __);
    -0.38
    uities
    -0.38
    POSITIVE LOGITS
     '\\;'
    0.62
    played
    0.61
     autorytatywna
    0.61
     reversal
    0.55
    playing
    0.53
     revers
    0.49
    Played
    0.49
     played
    0.49
    play
    0.47
    Royce
    0.46
    Activations Density 0.103%

    No Known Activations