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. 20-GEMMASCOPE-RES-16K
    6. 2268
    Prev
    Next
    INDEX
    Explanations

    proper nouns and names related to various subjects, including people and locations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    starting with "av" or "ev"

    np_acts-logits-general · gemini-2.0-flash

    Names starting with L, C, A, V, E, or S

    np_acts-logits-general · gemini-2.5-flash-lite
    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
    UpInside
    -0.75
    arrings
    -0.65
    createCanvas
    -0.65
     resourceCulture
    -0.59
    er
    -0.58
    ngrx
    -0.57
    ???:
    -0.57
    rungsseite
    -0.56
    ね
    -0.54
    حوالہ
    -0.54
    POSITIVE LOGITS
     WV
    0.70
     Merv
    0.67
    VY
    0.67
     mav
    0.66
     Mv
    0.64
     bv
    0.62
     MAV
    0.62
     Jove
    0.60
     fv
    0.60
     Vou
    0.60
    Activations Density 0.587%

    No Known Activations