Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 34-GEMMASCOPE-RES-16K
    6. 11006
    Prev
    Next
    INDEX
    Explanations

    information related to time periods and durations in studies or processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 34-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_34/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.34.hook_resid_post
    Hook Layer
    34
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     anno
    -0.50
     للاسماء
    -0.50
    boutin
    -0.47
    anterie
    -0.46
     EconPapers
    -0.45
    ſelves
    -0.43
    oneta
    -0.43
    Gambas
    -0.43
    UpdateCommand
    -0.42
    Jahres
    -0.42
    POSITIVE LOGITS
     days
    2.20
     Days
    1.90
    Days
    1.80
    days
    1.71
     DAYS
    1.67
     días
    1.47
     giorni
    1.43
    DAYS
    1.41
     Tagen
    1.38
     jours
    1.36
    Activations Density 0.464%

    No Known Activations