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

    Neuronpedia

    Jacobian LensNEW
    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. 0-GEMMASCOPE-RES-16K
    11. 14116
    Prev
    Next
    INDEX
    Explanations

    negative qualifiers that express denial or contradiction

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 0-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_0/width_16k/average_l0_129
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    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
    WebElementEntity
    -0.72
    featureID
    -0.71
    parsedMessage
    -0.67
     ſche
    -0.66
    IsMutable
    -0.65
     ſch
    -0.65
     Majefty
    -0.61
     ſind
    -0.60
    addCriterion
    -0.58
    Autoritní
    -0.57
    POSITIVE LOGITS
     whats
    0.37
     currently
    0.36
     youre
    0.36
     theyre
    0.36
     your
    0.35
    t
    0.35
    ves
    0.34
    KindOfClass
    0.34
     tracked
    0.34
    whats
    0.34
    Activations Density 0.257%

    No Known Activations