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. 5-GEMMASCOPE-RES-16K
    6. 10291
    Prev
    Next
    INDEX
    Explanations

    mathematical notations and symbols

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    IMENTAL
    -0.65
     tartalomajánló
    -0.61
    IndentedString
    -0.61
    amar
    -0.59
    antom
    -0.59
    ́s
    -0.59
     estimés
    -0.59
     Monfieur
    -0.59
    ANTO
    -0.58
    setMinimum
    -0.58
    POSITIVE LOGITS
    ğraf
    0.45
    tinyos
    0.45
    Obrázky
    0.45
     Мексичка
    0.44
    exitRule
    0.44
     acheteurs
    0.43
     στρα
    0.42
    antMatchers
    0.41
     suficientemente
    0.41
    bolista
    0.40
    Activations Density 1.568%

    No Known Activations