© 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. 16376
    Prev
    Next
    INDEX
    Explanations

    JavaScript function calls and DOM manipulation methods

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

    JavaScript's `getElementById` and attributes

    np_acts-logits-general · gemini-2.0-flash

    JavaScript DOM 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
    plus
    -0.63
    Plus
    -0.59
     character
    -0.57
    span
    -0.55
    PLUS
    -0.55
     Plus
    -0.55
     signe
    -0.53
    igne
    -0.53
    aw
    -0.53
     tren
    -0.53
    POSITIVE LOGITS
    (‘
    0.98
    ('
    0.95
    =’
    0.80
    berdayakan
    0.76
    (“
    0.69
    NameInMap
    0.69
     ('
    0.65
    ("
    0.65
    abestanden
    0.64
    ='
    0.63
    Activations Density 0.212%

    No Known Activations