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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    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. 4610
    Prev
    Next
    INDEX
    Explanations

    phrases related to personal identity and cultural experiences, particularly in the context of race and history

    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
     Reſ
    -0.76
     Eſ
    -0.70
     Conſ
    -0.68
     Perſ
    -0.68
     Inſ
    -0.64
     Anſ
    -0.63
     Houſe
    -0.61
     Diſ
    -0.61
     ſeveral
    -0.59
    ſelves
    -0.56
    POSITIVE LOGITS
     HasFactory
    0.48
     sebagainya
    0.46
     Audiodateien
    0.46
     بیشتری
    0.45
    ScopeManager
    0.45
     laikā
    0.45
     tarko
    0.44
     Picchu
    0.44
     şekilde
    0.44
     dolayı
    0.43
    Activations Density 1.095%

    No Known Activations