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. 9-GEMMASCOPE-RES-16K
    6. 7884
    Prev
    Next
    INDEX
    Explanations

    the start and end markers of the document

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_9/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    GEBURTSDATUM
    -1.38
    StoryboardSegue
    -1.32
     Италијани
    -1.23
    fromnode
    -1.19
    IntoConstraints
    -1.14
    хьтан
    -1.12
    setVerticalGroup
    -1.08
     ویکی‌پدی
    -1.07
    EndGlobalSection
    -1.01
     OFDb
    -1.00
    POSITIVE LOGITS
    \{\\
    0.62
    '
    0.51
    ’
    0.50
    ł
    0.42
     χαρα
    0.41
     fact
    0.39
     hän
    0.39
     et
    0.38
    <i>
    0.38
     lunak
    0.38
    Activations Density 0.014%

    No Known Activations