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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 30-GEMMASCOPE-RES-16K
    11. 12508
    Prev
    Next
    INDEX
    Explanations

    mentions of specific days, particularly emphasizing their significance in narrative contexts

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

    Time periods: day, night, summer

    np_acts-logits-general · gemini-2.0-flash

    day or night

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 30-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_30/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.30.hook_resid_post
    Hook Layer
    30
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     transfieras
    -0.52
    mergeFrom
    -0.50
     تضيفلها
    -0.49
     tonight
    -0.47
    今天
    -0.47
     مواليد
    -0.47
     heute
    -0.46
     idag
    -0.46
    今晚
    -0.45
     Today
    -0.45
    POSITIVE LOGITS
    蚪
    0.45
    Rever
    0.44
     rever
    0.44
    OfWeek
    0.44
     "..\..\
    0.43
    ptăm
    0.43
    큼
    0.43
    posedge
    0.42
     "..\..\..\
    0.42
    enment
    0.42
    Activations Density 0.202%

    No Known Activations