© 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-2-2B
    4. Residual Stream - 16k
    5. 7-GEMMASCOPE-RES-16K
    6. 4316
    Prev
    Next
    INDEX
    Explanations

    mentions of ordinal numbers in the context of events or rankings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 7-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_7/width_16k/average_l0_69
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Hook Layer
    7
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ,
    -0.61
     and
    -0.49
     surla
    -0.48
    if
    -0.46
    ValueGenerated
    -0.39
    .
    -0.36
    es
    -0.35
    local
    -0.35
    re
    -0.35
    The
    -0.35
    POSITIVE LOGITS
     Мексичка
    1.03
     незавершена
    1.03
    Viitteet
    1.03
    enumi
    0.90
    SequentialGroup
    0.87
    Pautan
    0.84
     الرياضيه
    0.83
     InputDecoration
    0.82
     المعيارى
    0.81
    Revenir
    0.81
    Activations Density 0.135%

    No Known Activations