© 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. 105395
    Prev
    Next
    INDEX
    Explanations

    code-related syntax and functions within programming languages

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

    code or markup attributes

    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
    featureID
    -0.68
     հղումներ
    -0.60
     transfieras
    -0.59
    +:+
    -0.53
     للاسماء
    -0.50
    BagConstraints
    -0.50
     iprot
    -0.49
    AndEndTag
    -0.49
    glTexCoord
    -0.48
    帖最后由
    -0.48
    POSITIVE LOGITS
     defaultstate
    0.52
     politiet
    0.47
    berdayakan
    0.46
     tradizionale
    0.41
     tradisional
    0.40
     traditionnel
    0.40
     traditionnels
    0.40
    épendant
    0.40
     čierna
    0.39
    ритори
    0.39
    Activations Density 0.016%

    No Known Activations