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

    Neuronpedia

    APICircuit 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. 5-GEMMASCOPE-RES-16K
    6. 10323
    Prev
    Next
    INDEX
    Explanations

    terms related to legal cases and judgments

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    комму
    -0.99
    mybatisplus
    -0.97
    clusal
    -0.94
     iprot
    -0.78
    iestety
    -0.77
    oodles
    -0.75
    setupUi
    -0.74
     Benth
    -0.73
    quatch
    -0.72
     bygga
    -0.72
    POSITIVE LOGITS
    er
    1.19
    rer
    0.97
    rrr
    0.92
    ror
    0.92
    ar
    0.84
    rrrrr
    0.83
    rr
    0.83
    rrrr
    0.82
    ir
    0.82
    ren
    0.80
    Activations Density 4.417%

    No Known Activations