© 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. 37-GEMMASCOPE-RES-16K
    11. 4735
    Prev
    Next
    INDEX
    Explanations

    details related to fingers and hands, especially in the context of actions and injuries

    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
    stdc
    -0.46
    Hentet
    -0.41
    FloatField
    -0.40
     виправивши
    -0.36
    InitVars
    -0.35
    ialog
    -0.35
     nahilalakip
    -0.35
     surla
    -0.33
     للمعارف
    -0.32
     Bikini
    -0.32
    POSITIVE LOGITS
     finger
    2.53
     fingers
    2.34
     Finger
    2.27
    Finger
    2.22
    finger
    2.22
     Fingers
    2.00
    fingers
    1.91
    Fingers
    1.87
     thumb
    1.80
     fingertips
    1.78
    Activations Density 0.427%

    No Known Activations