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. 10-GEMMASCOPE-RES-16K
    6. 4593
    Prev
    Next
    INDEX
    Explanations

    references to the concept of "two" or pairs

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    AddHtmlAttribute
    -0.59
    ثيق
    -0.57
     الرياضيه
    -0.56
    astéroïdes
    -0.54
    ^(@)
    -0.53
    Assemblée
    -0.53
    outWeight
    -0.50
    assemblée
    -0.49
     ſtate
    -0.48
     continúas
    -0.48
    POSITIVE LOGITS
    +#+#
    0.84
    apimachinery
    0.66
    fromCharCode
    0.60
    AutoField
    0.56
    ">//
    0.56
    fjspx
    0.55
     оба
    0.51
    ůj
    0.51
    MLLoader
    0.49
    帖最后由
    0.49
    Activations Density 0.881%

    No Known Activations