© 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. 34-GEMMASCOPE-RES-16K
    11. 8733
    Prev
    Next
    INDEX
    Explanations

    mentions of risks, challenges, and uncertainties associated with various topics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 34-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_34/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.34.hook_resid_post
    Hook Layer
    34
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     leia
    -0.34
     duquel
    -0.34
    ámenes
    -0.32
    onChangeText
    -0.31
     Klicken
    -0.31
     request
    -0.31
     glück
    -0.30
     march
    -0.30
     Aguilera
    -0.30
     colspan
    -0.30
    POSITIVE LOGITS
     involved
    1.55
    involved
    1.34
     Involved
    1.29
     INVOLVED
    1.19
     associated
    1.16
     entailed
    1.13
     involucrados
    1.02
     inherent
    0.93
    associated
    0.92
     attached
    0.89
    Activations Density 0.634%

    No Known Activations