© 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. 31-GEMMASCOPE-RES-16K
    6. 16147
    Prev
    Next
    INDEX
    Explanations

    references to data management, analysis, and reporting processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    technical documentation and procedural instructions related to software tools and systems.

    oai_token-act-pair · claude-4-5-haikuTriggered by @emiglarou
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_31/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.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     שוליים
    -0.71
    Hentet
    -0.45
    Erreferentziak
    -0.41
    znego
    -0.41
    httphttps
    -0.40
    diques
    -0.38
     autorytatywna
    -0.38
    lccn
    -0.37
    springframework
    -0.37
    HandlerContext
    -0.37
    POSITIVE LOGITS
     report
    2.08
     reports
    2.08
     Reports
    1.94
    reports
    1.85
    report
    1.84
     Report
    1.83
    Reports
    1.81
    Report
    1.77
     reporting
    1.75
     REPORTS
    1.68
    Activations Density 0.350%

    No Known Activations