© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 65k
    5. 0-GEMMASCOPE-RES-65K
    6. 9755
    Prev
    Next
    INDEX
    Explanations

    adjectives and their intensity in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 0-gemmascope-res-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_0/width_65k/average_l0_73
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    Data Type
    float32
    Hook Name
    blocks.0.hook_resid_post
    Hook Layer
    0
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Diwedd
    -0.93
    AndEndTag
    -0.92
    DoubleQuotes
    -0.91
    GEBURTS
    -0.85
    UrlResolution
    -0.84
     arşivlendi
    -0.83
    λευτα
    -0.82
     initComponents
    -0.82
    VersionUID
    -0.81
     насељу
    -0.81
    POSITIVE LOGITS
    '
    0.71
    ↵↵
    0.71
    .
    0.63
     (
    0.62
     kereszt
    0.55
     the
    0.55
    ,
    0.54
    ’
    0.54
    ↵
    0.54
    <bos>
    0.54
    Activations Density 0.793%

    No Known Activations