© 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. 38-GEMMASCOPE-RES-16K
    11. 7876
    Prev
    Next
    INDEX
    Explanations

    references to political claims and their scrutiny

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 38-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_38/width_16k/average_l0_128
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.38.hook_resid_post
    Hook Layer
    38
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    StoryboardSegue
    -0.91
     GenerationType
    -0.68
     Chwiliwch
    -0.63
    ModelSerializer
    -0.62
    dafx
    -0.62
    IsContent
    -0.61
    RegistryLite
    -0.60
    bootstrapcdn
    -0.58
    +#+
    -0.57
    oredCriteria
    -0.56
    POSITIVE LOGITS
     experts
    2.52
    experts
    2.11
     analysts
    2.05
    Experts
    1.95
     Experts
    1.93
     researchers
    1.91
     scientists
    1.87
     expertos
    1.85
     Experten
    1.77
     economists
    1.72
    Activations Density 0.809%

    No Known Activations