© 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-2-2B
    7. Residual Stream - 16k
    9. 22-GEMMASCOPE-RES-16K
    11. 10645
    Prev
    Next
    INDEX
    Explanations

    references to home damage and maintenance

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

    before file extensions or HTML/JS code

    np_acts-logits-general · gemini-2.0-flash

    interior flooring and doors

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    <bos>
    -0.52
    SuccessListener
    -0.51
    omycin
    -0.48
     Khas
    -0.47
    Bibliote
    -0.46
    ntesis
    -0.46
     Egon
    -0.46
    chow
    -0.46
    المناصب
    -0.46
    momix
    -0.45
    POSITIVE LOGITS
     laminate
    0.60
    دانشنامهٔ
    0.57
     refin
    0.56
     carpets
    0.56
    ValueGeneration
    0.56
     '\\;'
    0.55
     vinyl
    0.54
     lenker
    0.54
    abestanden
    0.53
     Lamin
    0.53
    Activations Density 0.045%

    No Known Activations