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. 23-GEMMASCOPE-RES-16K
    6. 12034
    Prev
    Next
    INDEX
    Explanations

    concepts related to legal matters and citizenship rights

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 23-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_23/width_16k/average_l0_75
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.hook_resid_post
    Hook Layer
    23
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     You
    -0.69
    You
    -0.68
     you
    -0.62
    you
    -0.60
    Your
    -0.55
     Your
    -0.54
     Please
    -0.53
     YOU
    -0.52
    Please
    -0.52
     please
    -0.51
    POSITIVE LOGITS
     Indeed
    0.91
    Viewed
    0.90
     Viewed
    0.89
    Indeed
    0.89
    こうした
    0.82
     Taken
    0.82
     Accordingly
    0.82
    Taken
    0.81
     Yet
    0.79
    Accordingly
    0.79
    Activations Density 0.528%

    No Known Activations