© 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. 31-GEMMASCOPE-RES-131K
    11. 9423
    Prev
    Next
    INDEX
    Explanations

    instances of the word "this," indicating a focus on specific references or points of discussion

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

    introducing research articles

    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
     ویکی‌پدی
    -0.48
    ündung
    -0.45
    Cyfarwyddwr
    -0.44
    adget
    -0.44
    ResponseWriter
    -0.44
    pyr
    -0.43
    nezeu
    -0.42
    RTLU
    -0.42
     blogs
    -0.42
    kaner
    -0.42
    POSITIVE LOGITS
    这一点
    0.59
    XmlAccessType
    0.52
     deshalb
    0.49
    ofern
    0.47
    这点
    0.47
     aspek
    0.47
     circunstancia
    0.47
     therefore
    0.47
     sentiment
    0.47
     ब्रेकडाउन
    0.47
    Activations Density 0.062%

    No Known Activations