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. 13-GEMMASCOPE-RES-16K
    6. 14041
    Prev
    Next
    INDEX
    Explanations

    marker tokens at the beginning of a document

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_13/width_16k/average_l0_84
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.13.hook_resid_post
    Hook Layer
    13
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ValueStyle
    -0.71
    ');?>
    -0.60
    cub
    -0.57
    ErrUnexpectedEOF
    -0.56
    MigrationBuilder
    -0.55
    CompleteListener
    -0.54
     PyTuple
    -0.54
    ConstraintMaker
    -0.53
    AutoresizingMask
    -0.52
    (;;)
    -0.51
    POSITIVE LOGITS
     resourceCulture
    0.53
     rezer
    0.52
     booking
    0.48
    archiviato
    0.48
     budgeting
    0.47
    Booking
    0.46
    booking
    0.46
    JAXB
    0.45
    érias
    0.45
     Budgeting
    0.45
    Activations Density 0.065%

    No Known Activations