© 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. 5869
    Prev
    Next
    INDEX
    Explanations

    terms indicating negation or limitation in arguments

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

    logical negation or contradiction words like "nor", "not", "does not", "isn't".

    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
     '\\;'
    -0.42
     manquante
    -0.41
     insuffisamment
    -0.40
     Evangelio
    -0.39
     navideña
    -0.39
     تضيفلها
    -0.36
     RSSSF
    -0.36
    PerformLayout
    -0.36
     Membre
    -0.36
     vVar
    -0.35
    POSITIVE LOGITS
     neither
    0.86
     nor
    0.84
    Neither
    0.82
    neither
    0.81
     Neither
    0.80
     tampoco
    0.74
    nor
    0.68
    InjectAttribute
    0.67
    Nor
    0.66
     siquiera
    0.63
    Activations Density 0.131%

    No Known Activations