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. 13669
    Prev
    Next
    INDEX
    Explanations

    phrases and terms related to effort, difficulty, or quality in various contexts

    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
    successfully
    -0.65
    pgsql
    -0.58
     unsuccessfully
    -0.58
     successfully
    -0.57
    новниш
    -0.55
    lysm
    -0.54
    rungsseite
    -0.53
    RenderAtEndOf
    -0.53
    parency
    -0.50
    Generalized
    -0.50
    POSITIVE LOGITS
    ful
    0.79
    worldly
    0.75
    worthy
    0.70
    tious
    0.66
    isome
    0.66
    orous
    0.66
    FUL
    0.65
    acious
    0.64
    tiful
    0.64
    vellous
    0.63
    Activations Density 0.404%

    No Known Activations