© 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. 18-GEMMASCOPE-RES-16K
    11. 846
    Prev
    Next
    INDEX
    Explanations

    mentions of knowledge and its various aspects in contexts related to healthcare and education

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

    "knowledge" followed by "of"

    np_acts-logits-general · gemini-2.0-flash

    knowledge of

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     relâche
    -0.69
    SizeF
    -0.65
    kész
    -0.61
    vál
    -0.59
    Mui
    -0.58
    oprecip
    -0.57
    ltk
    -0.57
    maline
    -0.56
    цездатний
    -0.56
    ApiModel
    -0.55
    POSITIVE LOGITS
     knowledge
    0.85
     Knowledge
    0.83
    Knowledge
    0.82
    knowledge
    0.79
     base
    0.71
    gain
    0.63
     Diſ
    0.63
    ')))
    0.62
    }';
    0.62
     about
    0.62
    Activations Density 0.100%

    No Known Activations