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. 15-GEMMASCOPE-RES-16K
    6. 8574
    Prev
    Next
    INDEX
    Explanations

    instances of the word "as" and its context in legal or formal text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_15/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Portail
    -0.60
    ⓧ
    -0.53
    ymce
    -0.51
    illah
    -0.51
     key
    -0.51
    adau
    -0.50
     embargo
    -0.48
    Rohan
    -0.48
    Adverten
    -0.47
    jstor
    -0.47
    POSITIVE LOGITS
    rungsseite
    0.83
    Personendaten
    0.71
    webElementXpaths
    0.69
    ValueStyle
    0.67
    signing
    0.65
    HasBeenSet
    0.62
    verwijspagina
    0.61
    yarnpkg
    0.55
    Havolalar
    0.54
     '{@
    0.52
    Activations Density 0.198%

    No Known Activations