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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 74
    Prev
    Next
    INDEX
    Explanations

    references to communication concepts and health-related discussions

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

    meaning "called" in different languages

    np_acts-logits-general · gemini-2.0-flash

    called something

    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
    volezza
    -0.45
    amante
    -0.41
    writeFieldEnd
    -0.40
    чика
    -0.38
     neby
    -0.38
    webElement
    -0.38
     vieill
    -0.37
    Datepicker
    -0.37
    ScopeManager
    -0.36
     verzorg
    -0.36
    POSITIVE LOGITS
    いわゆる
    0.75
     sogenannte
    0.72
     Called
    0.69
     tzw
    0.68
    Called
    0.62
     sogen
    0.60
    所謂
    0.60
     called
    0.59
    被称为
    0.59
    所谓的
    0.59
    Activations Density 1.499%

    No Known Activations