© 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-2-2B
    7. Residual Stream - 16k
    9. 17-GEMMASCOPE-RES-16K
    11. 11491
    Prev
    Next
    INDEX
    Explanations

    connections and relationships between entities or concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 17-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_17/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.17.hook_resid_post
    Hook Layer
    17
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Référence
    -0.59
    poort
    -0.42
     Kom
    -0.42
     Leaks
    -0.42
     tricks
    -0.40
     treu
    -0.40
     Bend
    -0.39
    FEL
    -0.39
    alama
    -0.39
     dri
    -0.39
    POSITIVE LOGITS
    同士
    1.19
     zweier
    1.16
     two
    1.14
     between
    1.14
     між
    1.11
     pairs
    1.09
     между
    1.07
    between
    1.05
    two
    1.04
     BETWEEN
    1.00
    Activations Density 0.889%

    No Known Activations