© 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. 19847
    Prev
    Next
    INDEX
    Explanations

    repeated sequences or long sequences in a technical context

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

    code snippets 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
    BoxShadow
    -0.47
    zA
    -0.46
     Wainwright
    -0.42
     références
    -0.41
     שוליים
    -0.40
    aA
    -0.40
    About
    -0.39
    A
    -0.39
    敢
    -0.38
    GLFW
    -0.37
    POSITIVE LOGITS
    fromnode
    0.72
     Numerade
    0.67
    celotti
    0.55
     الحره
    0.52
    \{\\
    0.51
    :✨
    0.50
     nakalista
    0.49
     parachoque
    0.49
    Tembelea
    0.47
     pelúcia
    0.46
    Activations Density 0.111%

    No Known Activations