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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    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. 3235
    Prev
    Next
    INDEX
    Explanations

    quantifiable measurements and specifications related to physical properties

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

    Calculations or references to surface area

    np_acts-logits-general · gemini-2.0-flash

    surface area

    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
     kasarigan
    -0.68
    TRAILING
    -0.67
    ArrowToggle
    -0.55
    ünstig
    -0.55
    TintMode
    -0.54
    tagHelperRunner
    -0.53
    gäng
    -0.50
    stridium
    -0.48
     AspNetCore
    -0.48
    틱
    -0.48
    POSITIVE LOGITS
     area
    1.83
     surface
    1.66
    area
    1.61
    Area
    1.61
     Area
    1.59
     volume
    1.56
     AREA
    1.49
     área
    1.44
    surface
    1.38
    AREA
    1.36
    Activations Density 0.560%

    No Known Activations