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

    Neuronpedia

    Jacobian LensNEW
    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-IT
    7. Residual Stream - 131k
    9. 9-GEMMASCOPE-RES-131K
    11. 60211
    Prev
    Next
    INDEX
    Explanations

    actions related to submersion or sinking

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

    sinking, sank, sunk

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_131k/average_l0_121
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    bibfield
    -0.49
    Trails
    -0.47
     paik
    -0.47
    luan
    -0.47
     buffered
    -0.46
     laſſen
    -0.46
     φύ
    -0.46
    getAdapter
    -0.45
     rå
    -0.45
    Anytime
    -0.44
    POSITIVE LOGITS
     sinking
    1.34
     sunk
    1.20
     sank
    1.02
     sunken
    0.96
     sink
    0.96
    sink
    0.92
     sinks
    0.87
     Sink
    0.84
    Sink
    0.75
     Sinks
    0.75
    Activations Density 0.008%

    No Known Activations