© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 0-GEMMASCOPE-RES-16K
    11. 9162
    Prev
    Next
    INDEX
    Explanations

    references to molecular topics or discussions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 0-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_0/width_16k/average_l0_129
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.hook_resid_post
    Hook Layer
    0
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     glaubt
    -0.52
    таратура
    -0.50
     glauben
    -0.47
     Commencez
    -0.46
    انجليز
    -0.46
     históricos
    -0.44
     voulons
    -0.44
    Oklahoma
    -0.44
     regering
    -0.43
    WithMany
    -0.43
    POSITIVE LOGITS
     points
    0.63
     features
    0.60
     verification
    0.59
     feature
    0.57
     Verification
    0.53
     atomic
    0.49
     nuclear
    0.49
     aspects
    0.48
    feature
    0.46
     Fame
    0.46
    Activations Density 0.249%

    No Known Activations