Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 38-GEMMASCOPE-RES-16K
    6. 8659
    Prev
    Next
    INDEX
    Explanations

    references to hand anatomy and movement

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 38-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_38/width_16k/average_l0_128
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.38.hook_resid_post
    Hook Layer
    38
    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
    -0.42
     nahilalakip
    -0.40
     surla
    -0.38
     للمعارف
    -0.38
    FloatField
    -0.36
    ialog
    -0.33
    Hentet
    -0.33
     Bullock
    -0.32
    contentLoaded
    -0.31
     бре
    -0.31
    POSITIVE LOGITS
     finger
    2.28
     fingers
    2.20
     Finger
    2.05
    Finger
    2.02
    finger
    2.02
     Fingers
    1.86
    fingers
    1.80
    Fingers
    1.76
     thumb
    1.75
     fingertips
    1.73
    Activations Density 0.476%

    No Known Activations