© 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 EvalsExportsinterp-engineNEWAPI 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. 11751
    Prev
    Next
    INDEX
    Explanations

    phrases and terms related to programming and network protocols

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

    Rust and JavaScript code snippets

    np_acts-logits-general · gemini-2.0-flash

    Rust keywords and identifiers

    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
     préférence
    -0.35
     Grüsse
    -0.33
    bollah
    -0.33
    issante
    -0.32
     cze
    -0.30
    darah
    -0.30
    lectricité
    -0.29
    Social
    -0.28
    zież
    -0.28
    typedef
    -0.28
    POSITIVE LOGITS
     nahilalakip
    0.83
    didSet
    0.69
     rhestr
    0.66
    دانشنامهٔ
    0.66
     ProtoMessage
    0.64
     للاسماء
    0.60
    Välislingid
    0.60
    Datuak
    0.60
    fjspx
    0.58
    onViewCreated
    0.57
    Activations Density 0.452%

    No Known Activations