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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 15-GEMMASCOPE-RES-16K
    6. 12783
    Prev
    Next
    INDEX
    Explanations

    coordinate and dimension attributes in a programming context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_15/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    rrggbb
    -0.59
     يتيمه
    -0.58
     onAnimation
    -0.56
    TintMode
    -0.55
    fillType
    -0.52
    httphttps
    -0.52
     OMIT
    -0.49
    loride
    -0.49
     newOwner
    -0.48
    CGPoint
    -0.47
    POSITIVE LOGITS
     thickness
    0.73
     diameter
    0.72
     sizeof
    0.72
     length
    0.69
     size
    0.66
    sizeof
    0.64
     footprint
    0.64
    sizeCache
    0.63
    strlen
    0.63
     width
    0.63
    Activations Density 0.494%

    No Known Activations