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. 36-GEMMASCOPE-RES-16K
    6. 14866
    Prev
    Next
    INDEX
    Explanations

    quantitative information, statistics, and numeric values

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 36-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_36/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.36.hook_resid_post
    Hook Layer
    36
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    IntoConstraints
    -0.37
     Dod
    -0.37
     resourceCulture
    -0.35
    jsxFileName
    -0.34
     xxvi
    -0.34
     Reference
    -0.31
     externi
    -0.31
    tvguidetime
    -0.31
     wave
    -0.31
     civil
    -0.31
    POSITIVE LOGITS
    PropertyChanging
    0.56
     pinulongan
    0.54
     estekak
    0.54
    躇
    0.52
     كومونز
    0.50
    AccessorTable
    0.49
     nonUne
    0.48
     الرياضيه
    0.47
     AssemblyCompany
    0.46
     HasFactory
    0.46
    Activations Density 0.733%

    No Known Activations