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-2-2B
    4. Residual Stream - 16k
    5. 21-GEMMASCOPE-RES-16K
    6. 6769
    Prev
    Next
    INDEX
    Explanations

    phrases or terms associated with legal representation and advocacy on behalf of individuals or entities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    IUrlHelper
    -0.84
     nakalista
    -0.82
     continúas
    -0.81
    IntoConstraints
    -0.78
    AccessorTable
    -0.77
     nahilalakip
    -0.77
    rungsseite
    -0.76
    invokeLater
    -0.76
     propOrder
    -0.74
    ImageContext
    -0.74
    POSITIVE LOGITS
     behalf
    2.29
     mewakili
    1.27
     representing
    1.09
     on
    1.07
     representación
    0.98
     represent
    0.96
     namens
    0.95
    representing
    0.92
     onbe
    0.90
    แทน
    0.89
    Activations Density 0.257%

    No Known Activations