© 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. 0-GEMMASCOPE-RES-16K
    11. 14865
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "shell" and its variations, as well as terms related to medical diagnosis

    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
     sudden
    -0.54
     op
    -0.50
     leading
    -0.49
     he
    -0.49
     declared
    -0.48
     Deputy
    -0.48
     visibly
    -0.48
     
    -0.48
     science
    -0.47
     Ju
    -0.47
    POSITIVE LOGITS
    parsedMessage
    0.87
    featureID
    0.76
     $_"
    0.76
    EndInit
    0.74
     ब्रेकडाउन
    0.65
    MessageOf
    0.64
    complexType
    0.62
    Diagnosis
    0.62
    存于互联网档案馆
    0.61
    UnknownFieldSet
    0.61
    Activations Density 0.314%

    No Known Activations