© 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. 39-GEMMASCOPE-RES-16K
    6. 4722
    Prev
    Next
    INDEX
    Explanations

    phrases related to historical interpretations of societal structures and indigenous cultures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 39-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_39/width_16k/average_l0_131
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.39.hook_resid_post
    Hook Layer
    39
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    enterOuterAlt
    -0.41
     démarche
    -0.41
     płyn
    -0.38
     dreapta
    -0.38
    -------------</
    -0.35
     vicenda
    -0.35
     orilla
    -0.35
     Fahr
    -0.35
     horen
    -0.34
     Herrn
    -0.34
    POSITIVE LOGITS
     religion
    0.83
     education
    0.79
     agriculture
    0.77
     religions
    0.76
     literacy
    0.75
     urbanization
    0.75
     illiteracy
    0.73
     Religion
    0.72
     economic
    0.71
     democracy
    0.71
    Activations Density 0.786%

    No Known Activations