© 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-2-9B
    7. Residual Stream - 16k
    9. 37-GEMMASCOPE-RES-16K
    11. 6103
    Prev
    Next
    INDEX
    Explanations

    variations of the word "under" indicating its prevalence or specific usage contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 37-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_37/width_16k/average_l0_124
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.37.hook_resid_post
    Hook Layer
    37
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     useCallback
    -0.35
    épendance
    -0.29
     uVar
    -0.28
    '>";
    -0.28
     arşivlendi
    -0.27
    โก
    -0.26
    Salta
    -0.26
     ]];
    -0.26
     }));
    -0.26
     giác
    -0.25
    POSITIVE LOGITS
    neath
    0.88
    utilized
    0.76
    belly
    0.76
    represented
    0.74
    appreciated
    0.74
    privileged
    0.71
    study
    0.71
    estimating
    0.71
    lining
    0.70
    performing
    0.68
    Activations Density 0.217%

    No Known Activations