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. 21-GEMMASCOPE-RES-16K
    6. 8550
    Prev
    Next
    INDEX
    Explanations

    references to political institutions and organizations

    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
     King
    -0.57
     +
    -0.55
    King
    -0.51
     Discover
    -0.50
    ,
    -0.48
     king
    -0.48
     related
    -0.47
     en
    -0.46
     -
    -0.46
    !
    -0.46
    POSITIVE LOGITS
    Personendaten
    0.88
     CreateTagHelper
    0.87
    DockStyle
    0.85
    InputBorder
    0.78
    SourceChecksum
    0.77
    tagHelperRunner
    0.76
    InjectAttribute
    0.75
     autorytatywna
    0.74
    ]--;
    0.74
    enderror
    0.71
    Activations Density 0.125%

    No Known Activations