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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & 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. 20-GEMMASCOPE-RES-16K
    6. 9702
    Prev
    Next
    INDEX
    Explanations

    components related to job listings in a programming context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 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
     Nacionales
    -0.60
     newState
    -0.53
    anskje
    -0.52
     Wię
    -0.47
     Nun
    -0.47
     Públicas
    -0.46
    ėk
    -0.45
     smtplib
    -0.45
     setUsername
    -0.45
     Krakowie
    -0.45
    POSITIVE LOGITS
     nakalista
    0.87
     HasFactory
    0.72
    formik
    0.67
     ModelExpression
    0.66
    WebVitals
    0.63
    ɵɵ
    0.63
    UnsafeEnabled
    0.59
     AssemblyVersion
    0.58
    ⎨
    0.58
     Lampard
    0.57
    Activations Density 0.103%

    No Known Activations