Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 4413
    Prev
    Next
    INDEX
    Explanations

    elements related to personal feelings and interpersonal relationships

    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
    nezeu
    -0.42
    newBuilder
    -0.36
    yfik
    -0.35
    клопе
    -0.35
    vermectin
    -0.35
    rawDesc
    -0.33
    <>(
    -0.33
    fano
    -0.33
    ğraf
    -0.32
     ErrIntOverflow
    -0.32
    POSITIVE LOGITS
     feel
    3.38
     feeling
    3.30
     feels
    3.11
    feel
    3.02
     felt
    2.98
    Feel
    2.95
     Feel
    2.88
    feeling
    2.88
     FEEL
    2.86
    feels
    2.69
    Activations Density 0.618%

    No Known Activations