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. 25-GEMMASCOPE-RES-16K
    6. 4333
    Prev
    Next
    INDEX
    Explanations

    occurrences of the letter 'E' 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 @ 25-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.hook_resid_post
    Hook Layer
    25
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ConstraintMaker
    -0.73
     EconPapers
    -0.69
     surla
    -0.62
     handleMessage
    -0.59
    RegressionTest
    -0.59
    archiviato
    -0.58
     '\\;'
    -0.53
    Hozzáférés
    -0.52
    sible
    -0.52
    ).__
    -0.50
    POSITIVE LOGITS
    :+:
    0.55
     ویکی‌پدی
    0.52
    ึ้น
    0.51
     Checks
    0.50
    Obrázky
    0.49
    ilish
    0.47
    FetchType
    0.47
     checks
    0.46
     jav
    0.46
    checks
    0.46
    Activations Density 0.204%

    No Known Activations