© 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. 7316
    Prev
    Next
    INDEX
    Explanations

    references to political figures, their actions, and associated controversies

    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
     says
    -0.87
     obviously
    -0.85
    says
    -0.84
     said
    -0.83
    obviously
    -0.79
     Says
    -0.77
     Obviously
    -0.76
     tentu
    -0.76
     oczywiście
    -0.75
     reportedly
    -0.73
    POSITIVE LOGITS
     actually
    0.71
     indeed
    0.70
     inderdaad
    0.67
     وأن
    0.65
    Actually
    0.63
     Actually
    0.63
    actually
    0.62
     efectivamente
    0.62
     aslında
    0.60
     ACTUALLY
    0.59
    Activations Density 1.605%

    No Known Activations