© 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. 34-GEMMASCOPE-RES-16K
    11. 10940
    Prev
    Next
    INDEX
    Explanations

    specific terminology related to technical components and processes

    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
    +#+
    -0.47
     myſelf
    -0.36
    :+:
    -0.36
     nadzieję
    -0.35
    ligheten
    -0.35
    ettbewer
    -0.34
    +-+-
    -0.33
     nélkül
    -0.33
     ſmall
    -0.33
     årets
    -0.32
    POSITIVE LOGITS
     itself
    0.85
     walls
    0.79
     shaft
    0.69
     internals
    0.69
     shafts
    0.67
     edges
    0.66
    本体
    0.66
    itself
    0.66
     blades
    0.65
     Itself
    0.65
    Activations Density 1.159%

    No Known Activations