Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 10722
    Prev
    Next
    INDEX
    Explanations

    terms related to biochemical or pharmaceutical substances, particularly those involving lipids and peptides

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

    Follows "ti," "catho," "vr," "o," or "liqu"

    np_acts-logits-general · gemini-2.0-flash

    liquids", "weird\/dos", "cathol\/des", "indiv\/dual"

    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
    出版年
    -0.52
     Italijanski
    -0.47
     Baillargeon
    -0.42
    rapment
    -0.39
     lượng
    -0.39
    scm
    -0.39
     समीक्षक
    -0.39
     صوتيه
    -0.38
    verticalLayout
    -0.38
    expandindo
    -0.38
    POSITIVE LOGITS
    ded
    0.94
     ids
    0.90
    ids
    0.88
    dify
    0.86
    ds
    0.85
    de
    0.84
    IDS
    0.76
    ides
    0.76
    Ids
    0.76
    IDs
    0.76
    Activations Density 0.605%

    No Known Activations