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-IT
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 74855
    Prev
    Next
    INDEX
    Explanations

    specific scientific terms and their relationships in medical or biological contexts

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

    patients treated with Stents

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     AssemblyCulture
    -0.80
     CreateTagHelper
    -0.69
    aarrggbb
    -0.66
    Rüyada
    -0.65
    ValueStyle
    -0.62
    GEBURTSDATUM
    -0.61
    basicConfig
    -0.61
    ьаж
    -0.61
     '\\;'
    -0.59
     Савезне
    -0.58
    POSITIVE LOGITS
     is
    0.42
     ren
    0.39
     nix
    0.36
     intptr
    0.36
     results
    0.34
     terp
    0.34
     opts
    0.34
     exceeds
    0.34
     goes
    0.33
    ONESIA
    0.33
    Activations Density 0.060%

    No Known Activations