© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 35-GEMMASCOPE-RES-16K
    6. 14749
    Prev
    Next
    INDEX
    Explanations

    details related to physical conditions and measurements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 35-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_35/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.35.hook_resid_post
    Hook Layer
    35
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    verwijspagina
    -0.37
    门
    -0.34
     kasarigan
    -0.32
     gasket
    -0.31
     Paddle
    -0.31
    Door
    -0.31
    sibilità
    -0.31
    ímetros
    -0.31
     gaskets
    -0.31
     danza
    -0.30
    POSITIVE LOGITS
     slope
    2.05
     slopes
    1.86
     hill
    1.77
    slope
    1.74
     Slope
    1.68
    Slope
    1.56
     hills
    1.53
     hillside
    1.52
     steep
    1.52
     sloping
    1.48
    Activations Density 0.440%

    No Known Activations