© 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. 20-GEMMASCOPE-RES-16K
    6. 708
    Prev
    Next
    INDEX
    Explanations

    terms and concepts related to health and wellness

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

    health-related words, particularly those indicating poor health or unhealthy conditions.

    oai_token-act-pair · claude-3-5-haiku-20241022Triggered by @neilrathi
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_16k/average_l0_68
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Portale
    -0.39
    United
    -0.38
    حياتها
    -0.37
    Others
    -0.36
    женный
    -0.34
     Versorgung
    -0.34
     vielen
    -0.33
     требований
    -0.33
     Belastung
    -0.33
     کسی
    -0.33
    POSITIVE LOGITS
    BibitemShut
    0.84
    httphttps
    0.78
     unſ
    0.70
     Shakspeare
    0.69
    ſelf
    0.66
    featureID
    0.66
     ་་
    0.66
    Revenir
    0.65
     ſich
    0.64
    ロウィン
    0.64
    Activations Density 0.358%

    No Known Activations