Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 1-GEMMASCOPE-RES-16K
    6. 5734
    Prev
    Next
    INDEX
    Explanations

    the presence of the letter "é" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.1.hook_resid_post
    Hook Layer
    1
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Theſe
    -0.84
     Anſ
    -0.80
     économies
    -0.80
     ainfi
    -0.76
    UnsafeEnabled
    -0.74
    englanniksi
    -0.73
     Beſ
    -0.72
     Inſ
    -0.69
     Lightboxes
    -0.69
    kháu
    -0.69
    POSITIVE LOGITS
    é
    4.05
    É
    2.14
    eacute
    2.06
    è
    1.67
     é
    1.62
    és
    1.52
    ée
    1.28
    Eacute
    1.24
     É
    1.22
    éz
    1.18
    Activations Density 0.039%

    No Known Activations