© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 65136
    Prev
    Next
    INDEX
    Explanations

    temporal expressions related to durations and specific time frames

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

    time periods in hours

    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
    routeProvider
    -0.55
    ßerdem
    -0.51
    MessageTagHelper
    -0.49
     Wisata
    -0.46
     coronel
    -0.45
     Penyakit
    -0.43
     invitado
    -0.43
    //
    -0.43
     Sakit
    -0.43
     OnTrigger
    -0.42
    POSITIVE LOGITS
     hours
    1.10
     HOURS
    0.85
    hours
    0.84
     Hours
    0.84
     horas
    0.78
    Hours
    0.78
     hour
    0.77
     days
    0.75
     hrs
    0.71
     HOUR
    0.71
    Activations Density 0.049%

    No Known Activations