© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 37-GEMMASCOPE-RES-16K
    11. 6726
    Prev
    Next
    INDEX
    Explanations

    numerical values and their associations in a structured format

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 37-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_37/width_16k/average_l0_124
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.37.hook_resid_post
    Hook Layer
    37
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    principalColumn
    -0.42
     stabilité
    -0.34
    Promise
    -0.31
    NSNumber
    -0.31
     promise
    -0.31
     granos
    -0.30
     Treue
    -0.30
    hdys
    -0.29
    wachsenen
    -0.29
     saman
    -0.29
    POSITIVE LOGITS
     transfieras
    0.77
     bit
    0.72
    Bit
    0.69
    OGND
    0.69
     Bit
    0.68
     BIT
    0.67
    bit
    0.66
     désolés
    0.63
    protoimpl
    0.62
     ball
    0.61
    Activations Density 0.565%

    No Known Activations