© 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 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. 31-GEMMASCOPE-RES-131K
    11. 89788
    Prev
    Next
    INDEX
    Explanations

    sections or phrases that indicate formal acknowledgments or disclosures in research articles

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

    labels and context

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 31-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_31/width_131k/average_l0_109
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    SequentialGroup
    -0.47
    setVerticalGroup
    -0.47
    了吧
    -0.42
    ついに
    -0.39
     unilaterally
    -0.38
     Audiodateien
    -0.38
    <eos>
    -0.38
     >=",
    -0.37
    DockStyle
    -0.37
     Normdatei
    -0.36
    POSITIVE LOGITS
     Context
    0.69
     circonst
    0.62
    Context
    0.60
    quelle
    0.60
     contexto
    0.59
     question
    0.58
     context
    0.57
     sentence
    0.57
     explain
    0.56
     interpret
    0.56
    Activations Density 0.007%

    No Known Activations