© 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. 23-GEMMASCOPE-RES-16K
    11. 5342
    Prev
    Next
    INDEX
    Explanations

    assertions of evidence or clarity regarding a subject or situation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 23-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_23/width_16k/average_l0_75
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.hook_resid_post
    Hook Layer
    23
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    MigrationBuilder
    -0.95
    GEBURTSDATUM
    -0.77
    mybatisplus
    -0.73
    fjspx
    -0.68
    adaptiveStyles
    -0.65
     للاسماء
    -0.65
    évaluateur
    -0.62
     referenties
    -0.58
    StreetMap
    -0.57
     समीक्षाओं
    -0.55
    POSITIVE LOGITS
     clear
    3.06
    clear
    2.52
     Clear
    2.25
     CLEAR
    2.25
     clearly
    2.24
    Clear
    2.18
     clearest
    1.99
    CLEAR
    1.97
     clearer
    1.96
    clearly
    1.94
    Activations Density 0.711%

    No Known Activations