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. 9718
    Prev
    Next
    INDEX
    Explanations

    elements related to user interface components and layout structures

    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
     tartalomajánló
    -1.31
    expandindo
    -1.19
    تقاوى
    -1.15
     &___
    -1.15
    +#+#
    -1.10
     Normdatei
    -1.08
    ArrowToggle
    -1.08
    ThroughAttribute
    -1.03
    setVerticalGroup
    -1.03
     >=",
    -0.99
    POSITIVE LOGITS
    col
    0.66
     col
    0.53
    w
    0.51
    -
    0.46
    Col
    0.46
    p
    0.45
    cy
    0.45
    /
    0.44
    y
    0.44
    lo
    0.44
    Activations Density 0.014%

    No Known Activations