© 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-IT
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 15064
    Prev
    Next
    INDEX
    Explanations

    references to web APIs and their endpoints

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

    Code snippets with file extensions

    np_acts-logits-general · gemini-2.0-flash

    URLs and file paths

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     AssemblyCulture
    -0.59
    SequentialGroup
    -0.53
     <>",
    -0.52
     Réponses
    -0.48
    Hentet
    -0.43
    észetes
    -0.42
     Chwiliwch
    -0.42
    UnsafeEnabled
    -0.42
    outState
    -0.39
    UIControlState
    -0.38
    POSITIVE LOGITS
     estimés
    0.49
     memp
    0.46
     FileWriter
    0.45
     Pingback
    0.44
    berdayakan
    0.44
     Structured
    0.43
     مشين
    0.43
     localhost
    0.43
     HasFactory
    0.42
    ligente
    0.42
    Activations Density 0.067%

    No Known Activations