Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 12711
    Prev
    Next
    INDEX
    Explanations

    programming constructs, particularly structure and function definitions

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

    Code structures containing "opcode_tid ot" unions

    np_acts-logits-general · gemini-2.0-flash

    declarations of int and boolean

    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-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    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
     pendapat
    -0.48
     iniciativas
    -0.46
     iniciativa
    -0.45
     yoksa
    -0.43
     spéciaux
    -0.42
     sorpresas
    -0.41
     Gerechtigkeit
    -0.41
    jahteraan
    -0.40
     pihaknya
    -0.40
     berdua
    -0.40
    POSITIVE LOGITS
    ValueStyle
    0.67
     Chwiliwch
    0.66
    tagPool
    0.65
     Administrativna
    0.64
     Мексичка
    0.62
    OrWhiteSpace
    0.59
    opsida
    0.57
    GOTREF
    0.56
    VIAF
    0.56
     propOrder
    0.55
    Activations Density 0.173%

    No Known Activations