© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 12528
    Prev
    Next
    INDEX
    Explanations

    technical terms and statistical data related to experimental results

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

    Percentages

    np_acts-logits-general · gemini-2.0-flash

    weight percent

    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
    BufferSize
    -0.43
    enumi
    -0.43
    ]<<
    -0.43
    \"></
    -0.41
     חיצוניים
    -0.41
    {{/
    -0.40
    WireFormatLite
    -0.40
    ској
    -0.40
    RTEE
    -0.39
     $\$
    -0.39
    POSITIVE LOGITS
     percentage
    2.69
     percent
    2.53
     Percentage
    2.38
     percentages
    2.37
    percentage
    2.35
    percent
    2.29
     Percent
    2.28
     PERCENT
    2.28
    Percentage
    2.27
    %
    2.24
    Activations Density 1.441%

    No Known Activations