© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 18-GEMMASCOPE-RES-16K
    11. 1646
    Prev
    Next
    INDEX
    Explanations

    terms related to blowing or bursts of air

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

    Forms of the word "blow"

    np_acts-logits-general · gemini-2.0-flash

    blow up and blow out

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Normdatei
    -0.80
    ImageContext
    -0.60
    QMetaType
    -0.55
    nloa
    -0.54
    WireFormatLite
    -0.53
    mM
    -0.52
    仲
    -0.52
     Réponses
    -0.52
    mmol
    -0.50
    ^(
    -0.50
    POSITIVE LOGITS
     blown
    1.40
     blow
    1.33
     blew
    1.30
    Blow
    1.24
     blowing
    1.21
     Blow
    1.21
    blown
    1.21
     blows
    1.16
    blow
    1.13
    blowing
    1.01
    Activations Density 0.045%

    No Known Activations