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. 21-GEMMASCOPE-RES-16K
    6. 742
    Prev
    Next
    INDEX
    Explanations

    sentences that express health issues and physical discomfort

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    bigoplus
    -0.54
     inasmuch
    -0.53
     deoarece
    -0.48
    Moreover
    -0.48
    bigsqcup
    -0.46
    odotus
    -0.45
    ต่อไป
    -0.42
     poiché
    -0.41
     notably
    -0.41
    tably
    -0.41
    POSITIVE LOGITS
     gotta
    1.10
     got
    1.08
     Been
    1.06
     gonna
    1.05
     Need
    1.01
     Got
    1.01
    Been
    0.98
    Gonna
    0.98
     need
    0.95
     Took
    0.95
    Activations Density 0.234%

    No Known Activations