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. 114060
    Prev
    Next
    INDEX
    Explanations

    terms related to diabetes and its complications

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

    diabetic patients, diabetes mellitus

    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
    -0.66
     AssemblyVersion
    -0.64
    DockStyle
    -0.60
    ſelves
    -0.59
    canestro
    -0.57
     typelib
    -0.56
     myſelf
    -0.55
     Anſ
    -0.54
     anonyme
    -0.53
    цездатний
    -0.53
    POSITIVE LOGITS
    ArgsConstructor
    0.49
    RSpec
    0.40
    BagConstraints
    0.39
    ่าว
    0.32
    Manbalar
    0.31
     andra
    0.31
     ChromeDriver
    0.30
    ɵɵ
    0.30
     gang
    0.29
    İstinadlar
    0.29
    Activations Density 0.111%

    No Known Activations