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. 8024
    Prev
    Next
    INDEX
    Explanations

    numbers and data pertaining to statistical analysis and research results

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

    Numbers after decimal points

    np_acts-logits-general · gemini-2.0-flash

    digits and numbers

    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
     typelib
    -0.71
    EndInit
    -0.66
     doInBackground
    -0.61
     AspNetCore
    -0.60
    省市镇
    -0.59
     continúas
    -0.57
    IsContent
    -0.57
     Audiodateien
    -0.56
    ViewFeatures
    -0.55
    RoutingModule
    -0.52
    POSITIVE LOGITS
    8
    1.05
    9
    1.01
     eighty
    0.97
    7
    0.93
     ninety
    0.92
     Eighty
    0.89
     seventy
    0.86
     Ninety
    0.85
     eighties
    0.85
     Seventy
    0.80
    Activations Density 0.843%

    No Known Activations