© 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. 25-GEMMASCOPE-RES-16K
    11. 15253
    Prev
    Next
    INDEX
    Explanations

    statements or hypotheses that question or evaluate scientific propositions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 25-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_25/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.hook_resid_post
    Hook Layer
    25
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    BibitemShut
    -0.37
     NAV
    -0.36
     rela
    -0.36
     passes
    -0.36
     availability
    -0.36
     opportun
    -0.36
    ſſe
    -0.36
    Familiar
    -0.36
    ueger
    -0.36
    ſel
    -0.36
    POSITIVE LOGITS
     hypothesis
    0.95
     hypotheses
    0.79
     hipótesis
    0.77
    hypothesis
    0.76
     evidence
    0.73
     Hypothesis
    0.71
     hypothesized
    0.71
    Evidence
    0.70
     Evidence
    0.69
    evidence
    0.69
    Activations Density 1.006%

    No Known Activations