© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 23-GEMMASCOPE-RES-16K
    11. 10270
    Prev
    Next
    INDEX
    Explanations

    terms related to scientific processes and methodologies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 23-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_23/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.hook_resid_post
    Hook Layer
    23
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    oa̍t
    -0.57
     zelve
    -0.55
    ngilizce
    -0.50
    лтамалар
    -0.50
    orithmic
    -0.50
     חיצוניים
    -0.50
     insurg
    -0.49
     للاسماء
    -0.49
    edel
    -0.49
     Prefer
    -0.49
    POSITIVE LOGITS
     of
    0.44
     χρήση
    0.40
     construction
    0.39
     certain
    0.37
     Ouverture
    0.35
     utilization
    0.35
     utilisation
    0.34
    ennung
    0.34
    folgung
    0.34
     использование
    0.34
    Activations Density 1.221%

    No Known Activations