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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlog/PodcastSlackPrivacy & 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. 21-GEMMASCOPE-RES-16K
    6. 7338
    Prev
    Next
    INDEX
    Explanations

    jQuery method calls and related syntax elements in code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     <<<<<<<<<<<<<<
    -0.87
    awtextra
    -0.82
    transQ
    -0.76
     chofe
    -0.72
    saraba
    -0.72
     @"/
    -0.69
     itſelf
    -0.69
    DoubleQuotes
    -0.69
     ſche
    -0.68
     Anſ
    -0.68
    POSITIVE LOGITS
     ""),
    0.43
    Linki
    0.42
    INGREDIENT
    0.42
    ")));
    0.42
    EventListener
    0.41
    ']?>
    0.41
     We
    0.41
    ForResult
    0.41
     komunikasi
    0.40
    classmethod
    0.39
    Activations Density 0.075%

    No Known Activations