© 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. 7120
    Prev
    Next
    INDEX
    Explanations

    mathematical notation and symbols

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

    Text or labels preceding equations or figures

    np_acts-logits-general · gemini-2.0-flash

    cross-referencing markers

    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
    diyesi
    -0.49
     (
    -0.46
    administrative
    -0.46
    loyees
    -0.45
    érôme
    -0.44
     —
    -0.44
    substituted
    -0.43
    Créditos
    -0.43
    QtWidgets
    -0.42
    represented
    -0.42
    POSITIVE LOGITS
     Theſe
    0.92
    UnusedPrivate
    0.92
    脚注の使い方
    0.84
    出版年
    0.82
    WithIOException
    0.82
    :✨
    0.81
    })).
    0.80
     للمعارف
    0.79
     Мексичка
    0.78
    IsMutable
    0.77
    Activations Density 2.424%

    No Known Activations