© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 131k
    5. 31-GEMMASCOPE-RES-131K
    6. 44079
    Prev
    Next
    INDEX
    Explanations

    references to the concept of "last" in various contexts related to time and events

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

    last followed by noun

    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
    WithString
    -0.30
    セス
    -0.28
     Tats
    -0.27
     있어
    -0.27
    drage
    -0.26
     feit
    -0.26
    get
    -0.26
     continúas
    -0.26
     lige
    -0.26
    ATURE
    -0.26
    POSITIVE LOGITS
     للمعارف
    1.02
     المعيارى
    0.77
    ########.
    0.77
    AnimationsModule
    0.77
     posled
    0.73
     last
    0.71
    Последние
    0.67
    ésultats
    0.66
     zwiſchen
    0.66
     vestiges
    0.66
    Activations Density 0.026%

    No Known Activations