© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 3154
    Prev
    Next
    INDEX
    Explanations

    expressions of excitement and positivity

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

    punctuation marks, particularly exclamation points, indicating strong emotion or emphasis.

    oai_token-act-pair · claude-3-5-haiku-20241022Triggered by @neilrathi
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_16k/average_l0_68
    Prompts (Dashboard)
    24,576 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
     كومونز
    -0.66
    httphttps
    -0.63
    Personendaten
    -0.62
    AutoModerator
    -0.59
    IsContent
    -0.57
    QMetaType
    -0.54
    舺
    -0.54
    IntoConstraints
    -0.53
    Portály
    -0.53
    UnusedPrivate
    -0.52
    POSITIVE LOGITS
    <eos>
    0.75
    ↵↵
    0.56
    ↵
    0.51
    #
    0.46
    J
    0.46
    NO
    0.42
     Gross
    0.42
     #
    0.42
    .
    0.41
    Gross
    0.40
    Activations Density 0.075%

    No Known Activations