© 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. 81682
    Prev
    Next
    INDEX
    Explanations

    instances of numerical values or statistics related to time or occurrences

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

    years in the future

    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
    UnusedPrivate
    -0.75
    Autoritní
    -0.71
    providedIn
    -0.66
    thâu
    -0.62
    elemField
    -0.61
     Administrativna
    -0.61
    RTEX
    -0.55
    IndentedString
    -0.54
    RTSC
    -0.54
    RTLI
    -0.54
    POSITIVE LOGITS
     futurs
    0.48
    future
    0.47
     future
    0.47
     prochaine
    0.46
     künf
    0.45
    来年
    0.44
    ientôt
    0.44
     futuras
    0.43
     avenir
    0.43
     budú
    0.42
    Activations Density 0.014%

    No Known Activations