© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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 - 131k
    9. 9-GEMMASCOPE-RES-131K
    11. 76140
    Prev
    Next
    INDEX
    Explanations

    closing braces in code, indicating the end of code blocks or structures

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

    programming method calls and foreign words

    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
    ">//
    -0.54
    rrggbb
    -0.49
    SequentialGroup
    -0.42
    évaluateur
    -0.40
    AndEndTag
    -0.40
    complexContent
    -0.38
    criminator
    -0.38
    <_>
    -0.36
    AddHtmlAttribute
    -0.36
    ValueStyle
    -0.35
    POSITIVE LOGITS
     виправивши
    0.61
     saites
    0.51
    ViewChild
    0.48
     recommandée
    0.47
     ExecuteAsync
    0.46
     vertes
    0.46
    obiettivo
    0.45
    RUnlock
    0.44
     onClose
    0.44
     piede
    0.44
    Activations Density 0.005%

    No Known Activations