© 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. 20-GEMMASCOPE-RES-16K
    11. 2449
    Prev
    Next
    INDEX
    Explanations

    terms related to immunizations and annual reports in various contexts

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

    references to academic publications, especially in economics, with a focus on annual reviews.

    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
     الحره
    -0.54
     thiệu
    -0.54
     gynhyrchwyd
    -0.52
     للاسماء
    -0.52
    IntoConstraints
    -0.52
    WebElementEntity
    -0.51
     дописавши
    -0.50
    Jîn
    -0.45
     صوتيه
    -0.45
     חיצוניים
    -0.44
    POSITIVE LOGITS
     season
    0.98
     annual
    0.98
     annuel
    0.94
     anuales
    0.91
     yearly
    0.91
    annual
    0.90
     anual
    0.90
     Annual
    0.90
    Annual
    0.90
     seasonal
    0.88
    Activations Density 0.302%

    No Known Activations