© 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. 14801
    Prev
    Next
    INDEX
    Explanations

    references to legal criteria and classifications

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

    Requirements for a specific status

    np_acts-logits-general · gemini-2.0-flash

    considered eligible or not

    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
    octanol
    -0.58
    getColumnIndex
    -0.57
    Scénario
    -0.56
     ModelExpression
    -0.55
    ूरत
    -0.54
     CGPoint
    -0.54
     adaptation
    -0.52
     Predicted
    -0.51
     adaptations
    -0.50
     paces
    -0.49
    POSITIVE LOGITS
     qualify
    1.25
     qualifies
    1.17
     counted
    1.12
     eligible
    1.07
     counts
    1.01
     considered
    0.98
     automatically
    0.96
     count
    0.96
     qualifying
    0.94
    eligible
    0.94
    Activations Density 1.035%

    No Known Activations