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. 1-GEMMASCOPE-RES-16K
    6. 7000
    Prev
    Next
    INDEX
    Explanations

    instances of the term "fil" and its variations in programming 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
    SizeMode
    -0.73
     saud
    -0.59
     cipolla
    -0.58
    ريقة
    -0.57
     franqu
    -0.56
     Chúng
    -0.56
    lihood
    -0.56
    μφωνα
    -0.53
    Уважа
    -0.52
     quitté
    -0.52
    POSITIVE LOGITS
    fil
    1.62
     Fil
    1.58
    Fil
    1.39
     fil
    1.38
    FIL
    1.32
    fill
    1.27
     FIL
    1.08
    FILL
    0.98
    Fill
    0.90
    filo
    0.76
    Activations Density 0.130%

    No Known Activations