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. 35819
    Prev
    Next
    INDEX
    Explanations

    concepts related to intervention effectiveness and community ownership

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

    former members, previously destitute

    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
    ailleurs
    -0.42
    LookAnd
    -0.39
    Distribuzione
    -0.39
    +#+#
    -0.39
    
    -0.39
    bram
    -0.36
     unsuccessfully
    -0.36
    iddhartha
    -0.35
    [--
    -0.35
     geldig
    -0.35
    POSITIVE LOGITS
     DialogInterface
    0.47
    хьтан
    0.46
    contentLoaded
    0.46
     informée
    0.45
     pokrač
    0.44
    CloseOperation
    0.44
     Vikipedi
    0.43
     Wages
    0.43
    RegressionTest
    0.42
     incredible
    0.42
    Activations Density 0.114%

    No Known Activations