© 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-2-2B
    4. Residual Stream - 16k
    5. 22-GEMMASCOPE-RES-16K
    6. 6256
    Prev
    Next
    INDEX
    Explanations

    jQuery-related code constructs and methods

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

    JavaScript code snippets using jQuery

    np_acts-logits-general · gemini-2.0-flash

    JavaScript element manipulation

    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
    SpringBootTest
    -0.65
    IsContent
    -0.62
    setArguments
    -0.59
     actionPerformed
    -0.59
    ("")]
    
    -0.58
    labelledby
    -0.58
    ForValue
    -0.57
    ighth
    -0.56
    詰め
    -0.56
    SQLException
    -0.56
    POSITIVE LOGITS
    attr
    0.59
    parents
    0.54
    find
    0.51
    val
    0.50
    html
    0.49
     attr
    0.47
    prop
    0.47
    mitos
    0.46
    VIAF
    0.46
    css
    0.45
    Activations Density 0.102%

    No Known Activations