© 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. 116294
    Prev
    Next
    INDEX
    Explanations

    elements related to user interface components and their data types

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

    type declarations and lengths

    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
     préparé
    -0.44
    hadiran
    -0.44
     conducción
    -0.43
     ویکی‌پدیا
    -0.42
     fréquent
    -0.41
     rendu
    -0.41
    ArgsConstructor
    -0.41
     venido
    -0.40
     parachute
    -0.40
     gagné
    -0.40
    POSITIVE LOGITS
    NSUInteger
    0.61
    uint
    0.59
    guint
    0.58
    NameInMap
    0.56
    int
    0.55
    unsigned
    0.54
    DWORD
    0.54
     int
    0.53
    UINTN
    0.53
     DWORD
    0.52
    Activations Density 0.106%

    No Known Activations