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. 15994
    Prev
    Next
    INDEX
    Explanations

    terms related to scientific concepts, particularly in biochemistry and molecular biology

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

    Follows the letter "H"

    np_acts-logits-general · gemini-2.0-flash

    H followed by specific abbreviations

    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
     historical
    -0.73
    Historical
    -0.69
    historical
    -0.64
     historic
    -0.61
    horizontal
    -0.59
    tilizers
    -0.56
    ệp
    -0.56
    getById
    -0.55
    alie
    -0.53
    html
    -0.53
    POSITIVE LOGITS
    bootstrapcdn
    0.72
    IntoConstraints
    0.71
    SequentialGroup
    0.69
     kaarangay
    0.68
     pylori
    0.65
     HRS
    0.64
     sapiens
    0.63
     HHS
    0.62
     οποία
    0.62
    TintMode
    0.60
    Activations Density 1.161%

    No Known Activations