© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 24-GEMMASCOPE-RES-16K
    6. 5241
    Prev
    Next
    INDEX
    Explanations

    terms related to cytotoxic effects and human cell interactions in scientific studies

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

    Cytotoxicity, proliferation, migration, or inhibition

    np_acts-logits-general · gemini-2.0-flash

    cytotoxicity, proliferation, migration tests

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_24/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     paž
    -0.33
     usually
    -0.33
     árvores
    -0.33
     neighbourhood
    -0.29
     Unglück
    -0.29
     сезон
    -0.28
    organizzazione
    -0.28
     hombros
    -0.28
     preocupaciones
    -0.28
     autorytatywna
    -0.27
    POSITIVE LOGITS
    tested
    0.78
     disambiguazione
    0.72
     Tested
    0.70
     '\\;'
    0.69
    Tested
    0.69
     testSet
    0.68
    bootstrapcdn
    0.67
     tested
    0.66
    testcase
    0.66
     Tests
    0.65
    Activations Density 2.539%

    No Known Activations