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. 5-GEMMASCOPE-RES-16K
    6. 12651
    Prev
    Next
    INDEX
    Explanations

    the presence of XML tags

    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
     NSCoder
    -0.81
    expandindo
    -0.77
    LookAnd
    -0.67
    GeneratedValue
    -0.63
    CloseOperation
    -0.61
     torchvision
    -0.60
    AutoField
    -0.58
     Athenians
    -0.57
     tqdm
    -0.57
     LIBR
    -0.57
    POSITIVE LOGITS
    ferencia
    0.61
    (__('
    0.57
    ASIS
    0.56
    ferenz
    0.56
    目の
    0.55
    льник
    0.55
    ussen
    0.54
    rungsseite
    0.53
    gdx
    0.53
    ISupport
    0.52
    Activations Density 0.148%

    No Known Activations