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. 5940
    Prev
    Next
    INDEX
    Explanations

    phrases involving comparisons or contrasts

    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
     authentique
    -0.60
     لئے
    -0.57
    endregion
    -0.56
    inflater
    -0.55
    ful
    -0.54
    '];?>
    -0.53
     exécu
    -0.53
    原始内容存档于
    -0.53
    manuel
    -0.52
     reik
    -0.52
    POSITIVE LOGITS
     On
    1.19
     behalf
    1.15
    On
    1.13
     وعلى
    1.12
     on
    1.07
     ON
    1.07
    isOn
    1.03
    OnThe
    0.98
    TemporalType
    0.98
    onthe
    0.90
    Activations Density 0.111%

    No Known Activations