© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 34-GEMMASCOPE-RES-16K
    11. 607
    Prev
    Next
    INDEX
    Explanations

    terms related to neurological conditions and their implications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 34-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_34/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.34.hook_resid_post
    Hook Layer
    34
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    
    -0.48
    ViewFeatures
    -0.44
     Structural
    -0.42
     hippocampus
    -0.42
    hima
    -0.41
    blich
    -0.41
    Structural
    -0.40
    tonode
    -0.40
     fiberglass
    -0.40
    Rc
    -0.39
    POSITIVE LOGITS
     motor
    0.95
    motor
    0.83
    Motor
    0.80
     Motor
    0.80
     MOTOR
    0.76
     motores
    0.70
    MOTOR
    0.67
     moteur
    0.66
     mouvements
    0.66
     Bewegungen
    0.66
    Activations Density 0.635%

    No Known Activations