© 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. 37-GEMMASCOPE-RES-16K
    6. 4247
    Prev
    Next
    INDEX
    Explanations

    terms related to user actions and interactions in a system or application

    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
     estekak
    -0.47
    Хьажоргаш
    -0.47
     שוליים
    -0.39
    Билгалдахарш
    -0.37
     HasFactory
    -0.34
    endphp
    -0.33
     episódios
    -0.32
    saraba
    -0.31
    DockStyle
    -0.30
    ProjectName
    -0.30
    POSITIVE LOGITS
     user
    3.38
     users
    3.13
     User
    2.95
     Users
    2.86
    user
    2.78
    User
    2.66
     USER
    2.64
    用户
    2.55
     USERS
    2.52
    Users
    2.48
    Activations Density 0.856%

    No Known Activations