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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsBlogSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 32k
    5. 12-GEMMASCOPE-RES-32K
    6. 1804
    Prev
    Next
    INDEX
    Explanations

    identifiers and parameters in programming code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-res/layer_12/width_32k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    32,768
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     createState
    -0.62
    Xna
    -0.60
    bellar
    -0.59
     quality
    -0.58
    CategoryName
    -0.58
     qualit
    -0.57
    Quality
    -0.56
    abor
    -0.56
    BeginInit
    -0.56
    Климат
    -0.55
    POSITIVE LOGITS
    Personensuche
    0.84
    glGen
    0.72
     NSCoder
    0.66
     useParams
    0.65
    JoinColumn
    0.65
     UUID
    0.64
    GeneratedValue
    0.63
    HasForeignKey
    0.62
    UUID
    0.61
     getId
    0.60
    Activations Density 0.167%

    No Known Activations