© 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. 3260
    Prev
    Next
    INDEX
    Explanations

    classes, injections, and their relationships to credit and loan management

    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
     whoever
    -0.61
    probably
    -0.57
     probably
    -0.57
     Probably
    -0.54
    Probably
    -0.54
     гораздо
    -0.53
     almost
    -0.52
     rất
    -0.52
     vieles
    -0.52
    whatever
    -0.51
    POSITIVE LOGITS
     quelconque
    0.92
     particolarmente
    0.75
     perchance
    0.74
     alguno
    0.73
     вдруг
    0.71
     any
    0.69
     truly
    0.69
     jemals
    0.69
     anything
    0.68
     yoksa
    0.68
    Activations Density 0.935%

    No Known Activations