© 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 EvalsExportsinterp-engineNEWAPI 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. 42650
    Prev
    Next
    INDEX
    Explanations

    proper nouns, particularly names and specific labels

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

    Cara, Kara

    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
    transQ
    -0.44
     Edmond
    -0.34
     zich
    -0.34
    ựng
    -0.33
     not
    -0.33
    хотво
    -0.33
    gebung
    -0.32
     윤
    -0.32
     היו
    -0.32
     Ph
    -0.32
    POSITIVE LOGITS
    Cara
    2.42
     Cara
    2.39
     cara
    2.27
    cara
    1.87
    CARA
    1.52
     caras
    1.42
     carapace
    1.16
    caras
    1.09
     Kara
    0.90
    caro
    0.87
    Activations Density 0.004%

    No Known Activations