© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 8092
    Prev
    Next
    INDEX
    Explanations

    concepts related to patient beliefs and expectations regarding their health and treatments

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

    words and phrases related to personal beliefs, expectations, and attitudes.

    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
    bootstrapcdn
    -0.73
    ttemberg
    -0.64
     الرياضيه
    -0.59
     ब्रेकडाउन
    -0.59
    ✷
    -0.58
     pleaſure
    -0.57
    addContainerGap
    -0.56
    ロウィン
    -0.56
    ésultats
    -0.56
    reportWebVitals
    -0.56
    POSITIVE LOGITS
     belief
    0.71
     beliefs
    0.69
     croy
    0.59
     perception
    0.58
     perceptions
    0.56
     views
    0.56
     believes
    0.56
     creencias
    0.54
    Belief
    0.50
    belief
    0.50
    Activations Density 0.296%

    No Known Activations