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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & 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. 20-GEMMASCOPE-RES-16K
    6. 9931
    Prev
    Next
    INDEX
    Explanations

    references to various medical conditions and treatments, particularly those related to Parkinson's disease and related genetic factors

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    WebVitals
    -0.70
    ed
    -0.69
    ete
    -0.60
     metav
    -0.59
    i
    -0.58
     sanguí
    -0.57
    ett
    -0.57
    Biographie
    -0.56
    toPromise
    -0.54
     >=",
    -0.53
    POSITIVE LOGITS
    ded
    0.90
    ding
    0.77
    DDDD
    0.71
    der
    0.68
     faſt
    0.68
    dddd
    0.67
    locked
    0.67
     oreille
    0.65
    died
    0.64
     ―――――
    0.63
    Activations Density 1.360%

    No Known Activations