© 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. 9-GEMMASCOPE-RES-131K
    11. 128288
    Prev
    Next
    INDEX
    Explanations

    programming-related identifiers and structures

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

    code keywords and types

    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-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_131k/average_l0_121
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    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
    toxicity
    -0.35
     ब्रेकडाउन
    -0.34
    setcounter
    -0.29
    isinstance
    -0.29
     internally
    -0.27
     Italijanski
    -0.26
     élector
    -0.26
    europa
    -0.25
    ыгана
    -0.24
    setdefault
    -0.24
    POSITIVE LOGITS
    AttributeSet
    1.52
    HttpPost
    1.14
    IActionResult
    1.13
    HttpGet
    1.11
     IConfiguration
    1.10
    PropertyGroup
    1.07
    ApplicationTests
    1.02
    allowNull
    0.98
    onPressed
    0.87
     AttributeSet
    0.85
    Activations Density 0.001%

    No Known Activations