© 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. 40-GEMMASCOPE-RES-16K
    11. 1686
    Prev
    Next
    INDEX
    Explanations

    programmatic elements related to file handling or data upload states

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 40-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_40/width_16k/average_l0_125
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.40.hook_resid_post
    Hook Layer
    40
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    IsMutable
    -0.75
    Personendaten
    -0.70
     дописавши
    -0.68
    Сылтамалар
    -0.64
    expandindo
    -0.64
     Runs
    -0.63
    Examine
    -0.63
    Runs
    -0.63
    threw
    -0.61
    Reads
    -0.61
    POSITIVE LOGITS
     write
    0.46
     draw
    0.46
     wash
    0.46
     wear
    0.45
     build
    0.44
     install
    0.43
     buy
    0.42
     carry
    0.41
     cook
    0.41
     sell
    0.40
    Activations Density 0.577%

    No Known Activations