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

    Neuronpedia

    APISteerSAE EvalsBlog/PodcastNEWSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    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. 4267
    Prev
    Next
    INDEX
    Explanations

    references to individuals and groups related to sports and politics

    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
    EDEFAULT
    -0.82
     Audiodateien
    -0.80
    IntoConstraints
    -0.70
    AddTagHelper
    -0.69
     محفوظة
    -0.65
     Theſe
    -0.64
    OCCURRED
    -0.64
    Rhestr
    -0.64
     تانيه
    -0.63
    IsMutable
    -0.63
    POSITIVE LOGITS
     vying
    0.67
     worth
    0.65
     worthy
    0.65
     taking
    0.60
     awaiting
    0.59
     capable
    0.58
     poised
    0.56
     deserving
    0.56
     eligible
    0.55
     waiting
    0.54
    Activations Density 0.335%

    No Known Activations