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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 35-GEMMASCOPE-RES-16K
    6. 12379
    Prev
    Next
    INDEX
    Explanations

    elements related to numerical data and specifications in programming contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 35-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_35/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.35.hook_resid_post
    Hook Layer
    35
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ">${
    -0.57
     ${{
    -0.56
    tvguidetime
    -0.52
    sizeCache
    -0.51
     }}$}
    -0.50
    請繼續往下閱讀
    -0.49
     vPvB
    -0.48
    verwijspagina
    -0.48
    '>{
    -0.47
    ValueStyle
    -0.47
    POSITIVE LOGITS
     \
    1.66
    \
    1.21
     "\
    1.02
    .\
    1.01
    :\
    1.00
     (\
    0.99
    ,\
    0.98
    ;\
    0.93
     '\
    0.93
    -\
    0.91
    Activations Density 0.945%

    No Known Activations