© 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. 35-GEMMASCOPE-RES-16K
    11. 14199
    Prev
    Next
    INDEX
    Explanations

    statements related to evidence and claims, particularly in a legal context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 35-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_35/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.35.hook_resid_post
    Hook Layer
    35
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     kiệm
    -0.53
    :✨
    -0.51
    ardust
    -0.47
    matchCondition
    -0.47
     <<<<<<<<<<<<<<
    -0.46
     EconPapers
    -0.44
     kasarigan
    -0.43
     ffilmiau
    -0.43
    хьтан
    -0.42
    唆
    -0.41
    POSITIVE LOGITS
     presentation
    3.17
     presenting
    2.98
     presented
    2.95
     Presentation
    2.84
    Presentation
    2.69
     presentations
    2.69
     Presenting
    2.69
    presentation
    2.66
    Presenting
    2.64
    presented
    2.61
    Activations Density 0.836%

    No Known Activations