© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 22-GEMMASCOPE-RES-16K
    11. 12680
    Prev
    Next
    INDEX
    Explanations

    numerical statistics and figures, particularly related to performance metrics and comparisons

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

    numbers or totals

    np_acts-logits-general · gemini-2.0-flash

    highest figures or totals

    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
     nahilalakip
    -0.78
    GEBURTSDATUM
    -0.67
    GraphicsUnit
    -0.66
    principalTable
    -0.57
    WriteTagHelper
    -0.55
    Erreferentziak
    -0.55
    styleType
    -0.53
     setuptools
    -0.53
    XMLSchema
    -0.52
     proprietà
    -0.52
    POSITIVE LOGITS
     figure
    2.34
     figures
    1.90
    figure
    1.84
    figures
    1.63
     FIGURES
    1.41
     Figures
    1.35
     Figure
    1.29
    gure
    1.29
     FIGURE
    1.28
     cifra
    1.25
    Activations Density 0.416%

    No Known Activations