© 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 - 16k
    9. 9-GEMMASCOPE-RES-16K
    11. 7041
    Prev
    Next
    INDEX
    Explanations

    phrases indicating duration and frequency of activities or events

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

    Time periods: day, night, month

    np_acts-logits-general · gemini-2.0-flash

    all day and night

    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-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    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
    diteur
    -0.39
     findById
    -0.34
     hembra
    -0.34
    Frem
    -0.33
    amerika
    -0.32
    QtWidgets
    -0.32
     userName
    -0.31
     Frem
    -0.31
    ponenten
    -0.30
    ViewChild
    -0.29
    POSITIVE LOGITS
    throughout
    0.93
     throughout
    0.93
    Throughout
    0.88
     Throughout
    0.85
     sepanjang
    0.72
     يتيمه
    0.65
     boyunca
    0.61
    Across
    0.59
    一路
    0.59
     весь
    0.58
    Activations Density 0.159%

    No Known Activations