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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsBlogSlackPrivacy & 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. 12-GEMMASCOPE-RES-16K
    6. 5036
    Prev
    Next
    INDEX
    Explanations

    elements related to images and their attributes in HTML

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     nak
    -0.44
    ITOS
    -0.43
     T
    -0.43
    antik
    -0.42
     Cro
    -0.40
     Pac
    -0.40
     k
    -0.40
     C
    -0.40
    FI
    -0.39
    alia
    -0.39
    POSITIVE LOGITS
    mybatisplus
    0.92
    IsMutable
    0.90
    ConstraintMaker
    0.84
    LookAnd
    0.82
    ErrUnexpectedEOF
    0.76
    NameInMap
    0.75
     disant
    0.75
     ویکی‌پدیای
    0.73
     saying
    0.73
     caption
    0.73
    Activations Density 0.361%

    No Known Activations