© 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. 20-GEMMASCOPE-RES-16K
    11. 7077
    Prev
    Next
    INDEX
    Explanations

    criticisms and discussions surrounding historical injustices related to slavery

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

    End of sentences and interjections

    np_acts-logits-general · gemini-2.0-flash

    judgments and opinions

    np_acts-logits-general · gemini-2.5-flash-lite
    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
    حياته
    -0.54
    Synonymes
    -0.52
    SourceChecksum
    -0.49
    AnchorStyles
    -0.48
     vardır
    -0.47
    förs
    -0.47
     pernas
    -0.47
     جمعه
    -0.47
    جغرافيا
    -0.46
     cetera
    -0.46
    POSITIVE LOGITS
    Kudos
    0.92
     Shame
    0.82
     Kudos
    0.81
     shame
    0.78
     pathetic
    0.77
     why
    0.76
     smh
    0.76
     Seems
    0.76
    看來
    0.73
     Hopefully
    0.71
    Activations Density 0.366%

    No Known Activations