© 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. 3-GEMMASCOPE-RES-16K
    11. 5998
    Prev
    Next
    INDEX
    Explanations

    expressions about the significance or relevance of a concept or phenomenon

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_3/width_16k/average_l0_90
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     major
    -0.40
    Autoritní
    -0.40
    有力
    -0.36
    major
    -0.34
    叫
    -0.33
     funny
    -0.31
    openModal
    -0.31
     shiny
    -0.30
     studio
    -0.30
    덟
    -0.30
    POSITIVE LOGITS
     importance
    3.59
     Importance
    3.16
    importance
    3.11
    Importance
    3.06
     importancia
    2.67
     importância
    2.44
    importanza
    2.30
     significance
    2.23
     importanza
    2.13
     Bedeutung
    2.08
    Activations Density 0.080%

    No Known Activations