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. 11-GEMMASCOPE-RES-16K
    6. 6111
    Prev
    Next
    INDEX
    Explanations

    terms related to processes of explanation and reasoning

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Hook Layer
    11
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    denly
    -0.59
    Revenir
    -0.58
    specialchars
    -0.56
    lında
    -0.56
    messageInfo
    -0.55
     références
    -0.55
     initComponents
    -0.54
    ganu
    -0.53
    initializeApp
    -0.52
     continuant
    -0.51
    POSITIVE LOGITS
     '\\;'
    0.75
     المعيارى
    0.71
    Халык
    0.57
    aarrggbb
    0.56
     lye
    0.53
    irical
    0.53
    ings
    0.53
    FormTagHelper
    0.52
    কার
    0.50
     Anbau
    0.49
    Activations Density 0.736%

    No Known Activations