© 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. 95126
    Prev
    Next
    INDEX
    Explanations

    headings and title elements in HTML documents

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

    <h1> tag and directory listing

    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
     zwiſchen
    -0.57
     snippetHide
    -0.56
    ooc
    -0.56
    DotNetBar
    -0.56
    apeno
    -0.55
    olingo
    -0.54
    onOptions
    -0.54
     queſta
    -0.53
    ロウィン
    -0.52
     zuſammen
    -0.51
    POSITIVE LOGITS
    <h1>
    0.56
     inalámb
    0.43
     inalámbrica
    0.36
     térmico
    0.35
     térmica
    0.35
     sintética
    0.34
     türlü
    0.34
     pria
    0.33
    Inggris
    0.33
    不同的
    0.32
    Activations Density 0.000%

    No Known Activations