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-2-2B
    4. Residual Stream - 16k
    5. 19-GEMMASCOPE-RES-16K
    6. 15792
    Prev
    Next
    INDEX
    Explanations

    the beginning of a new document or a major structural element in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 19-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_19/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Hook Layer
    19
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     freshly
    -0.45
     lit
    -0.43
    blau
    -0.43
    шой
    -0.42
     murale
    -0.42
    foque
    -0.41
    ară
    -0.41
    fo
    -0.41
     ikinci
    -0.38
     papal
    -0.38
    POSITIVE LOGITS
     ModelExpression
    1.77
    GEBURTSDATUM
    1.65
     CreateTagHelper
    1.65
     ProtoMessage
    1.64
    InjectAttribute
    1.56
    MigrationBuilder
    1.51
    LookAnd
    1.50
    webElementXpaths
    1.50
     nahilalakip
    1.42
     <<<<<<<<<<<<<<
    1.40
    Activations Density 0.085%

    No Known Activations