© 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-IT
    7. Residual Stream - 16k
    9. 9-GEMMASCOPE-RES-16K
    11. 6300
    Prev
    Next
    INDEX
    Explanations

    terms related to mathematical or logical conjectures and constructs in programming

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Tokens starting with "con"

    np_acts-logits-general · gemini-2.0-flash

    words starting with 'con'

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     méri
    -0.59
     automatiques
    -0.59
     médié
    -0.57
     infancia
    -0.57
     grecque
    -0.56
     salvación
    -0.55
    basicConfig
    -0.54
     médicale
    -0.54
     virgen
    -0.54
     chré
    -0.54
    POSITIVE LOGITS
     Con
    1.70
    Con
    1.67
    con
    1.66
     CON
    1.49
    CON
    1.38
     con
    1.36
    Кон
    1.12
     Кон
    1.12
     kon
    1.12
     Kon
    1.09
    Activations Density 0.336%

    No Known Activations