© 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 - 131k
    9. 20-GEMMASCOPE-RES-131K
    11. 53608
    Prev
    Next
    INDEX
    Explanations

    terms related to defects and corrective actions in reports

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

    corrective action, analysis, intervention

    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-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    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
     Normdatei
    -0.55
     تضيفلها
    -0.51
     незавершена
    -0.48
     femei
    -0.40
    FieldBuilder
    -0.40
    évaluateur
    -0.40
    charCodeAt
    -0.40
     *
    -0.40
    ViewFeatures
    -0.40
    zembro
    -0.38
    POSITIVE LOGITS
    Erstellt
    0.48
    OLVED
    0.47
    enterOuterAlt
    0.44
    Semoga
    0.42
    consulté
    0.40
     AssemblyCompany
    0.38
     principio
    0.37
    success
    0.37
    Комментарий
    0.37
    processable
    0.37
    Activations Density 0.050%

    No Known Activations