© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 4-GEMMASCOPE-RES-16K
    6. 9917
    Prev
    Next
    INDEX
    Explanations

    references to "El" followed by a number or related entity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.hook_resid_post
    Hook Layer
    4
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Anſ
    -0.97
     raiſ
    -0.92
     anún
    -0.85
    titleMargin
    -0.81
     debout
    -0.79
    참고
    -0.79
     Plutarch
    -0.79
    twimg
    -0.78
    []{"
    -0.78
     photolibrary
    -0.78
    POSITIVE LOGITS
     El
    2.60
     el
    2.41
    El
    2.21
     EL
    1.95
    EL
    1.63
    el
    1.57
     Эль
    1.37
     Ел
    1.26
    エル
    1.19
     Els
    1.15
    Activations Density 0.061%

    No Known Activations