© 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. 25-GEMMASCOPE-RES-16K
    11. 15569
    Prev
    Next
    INDEX
    Explanations

    descriptive elements related to body parts and their conditions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 25-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_25/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.hook_resid_post
    Hook Layer
    25
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     AspNetCore
    -0.39
     AppCompatTheme
    -0.37
    addCriterion
    -0.35
     Rumuni
    -0.34
     cheval
    -0.34
     field
    -0.33
    djangoproject
    -0.32
    FieldBuilder
    -0.32
     roof
    -0.32
    kegaard
    -0.32
    POSITIVE LOGITS
    finger
    0.93
    Hands
    0.93
     fingers
    0.90
     finger
    0.90
     Hands
    0.89
     hand
    0.86
     guantes
    0.85
     glove
    0.85
    hands
    0.84
     Finger
    0.84
    Activations Density 0.458%

    No Known Activations