© 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 - 16k
    5. 9-GEMMASCOPE-RES-16K
    6. 5879
    Prev
    Next
    INDEX
    Explanations

    references to astronomical events and seasonal cycles related to pagan festivals

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

    Time periods, cycles, or light

    np_acts-logits-general · gemini-2.0-flash

    daylight and seasonal cycles

    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
    Вз
    -0.41
     nicio
    -0.37
     Hildebrand
    -0.35
    Confirmation
    -0.35
    ESOME
    -0.35
     blow
    -0.35
     dată
    -0.34
     Blow
    -0.34
     mergeFrom
    -0.34
     expulsion
    -0.33
    POSITIVE LOGITS
     Sols
    0.52
    daylight
    0.51
     مشين
    0.50
     SEDS
    0.49
     transfieras
    0.49
    Erreferentziak
    0.49
    Atsauces
    0.48
    Derbyniad
    0.48
     sumpay
    0.48
    Autoritní
    0.46
    Activations Density 0.284%

    No Known Activations