Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 19-GEMMASCOPE-RES-16K
    6. 338
    Prev
    Next
    INDEX
    Explanations

    legal terminology and concepts related to objections and motions in court proceedings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 19-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_19/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Hook Layer
    19
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    audiovisuel
    -0.54
    قایناقلار
    -0.51
    Autoritní
    -0.49
    出版年
    -0.49
    InputBorder
    -0.47
    styleType
    -0.46
     Савезне
    -0.45
     Vordergrund
    -0.44
     lenker
    -0.43
     foramen
    -0.43
    POSITIVE LOGITS
     resistance
    2.69
     Resistance
    2.28
    resistance
    2.23
    Resistance
    2.20
     resist
    2.17
     opposition
    2.08
     resisted
    2.04
     RESISTANCE
    2.04
     resisting
    2.03
     résistance
    1.98
    Activations Density 0.569%

    No Known Activations