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. 5-GEMMASCOPE-RES-16K
    6. 1407
    Prev
    Next
    INDEX
    Explanations

    occurrences of parentheses and grouping symbols in code or text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    //});
    -0.66
     تانيه
    -0.63
    География
    -0.62
     Мексичка
    -0.61
    tagHelperRunner
    -0.61
     bēr
    -0.60
    енча
    -0.57
    pakatan
    -0.57
     Brabant
    -0.56
     useContext
    -0.55
    POSITIVE LOGITS
    (!(
    0.73
     (!(
    0.65
    AnchorStyles
    0.64
    expandindo
    0.63
     Roskov
    0.57
    Activités
    0.57
    SequentialGroup
    0.57
    (&(
    0.56
    *(
    0.56
     صوتيه
    0.54
    Activations Density 0.222%

    No Known Activations