© 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
    7. Residual Stream - 16k
    9. 33-GEMMASCOPE-RES-16K
    11. 1845
    Prev
    Next
    INDEX
    Explanations

    specific protein patterns and gene identifiers related to molecular biology

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 33-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_33/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.33.hook_resid_post
    Hook Layer
    33
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     cæ
    -0.52
     ſta
    -0.50
     ſmall
    -0.50
     ſte
    -0.47
     houſe
    -0.43
     ſtre
    -0.41
     cauſe
    -0.40
     ſtand
    -0.40
     ſt
    -0.39
     occaf
    -0.39
    POSITIVE LOGITS
     ModelExpression
    0.86
    +:+
    0.85
     ProtoMessage
    0.82
    GEBURTSDATUM
    0.82
     препратки
    0.81
    ftagPool
    0.79
    
    0.77
    ReusableCell
    0.76
    aarrggbb
    0.75
    MigrationBuilder
    0.75
    Activations Density 0.356%

    No Known Activations