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. 3-GEMMASCOPE-RES-16K
    6. 10158
    Prev
    Next
    INDEX
    Explanations

    details related to events or occurrences that have significant impacts on communities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    initComponents
    -0.52
    Head
    -0.51
    Географиясе
    -0.48
     TextAppearance
    -0.46
     női
    -0.44
    bootstrapcdn
    -0.43
    verein
    -0.41
     bross
    -0.40
    ery
    -0.40
    再说
    -0.40
    POSITIVE LOGITS
    orianCalendar
    0.71
    PINES
    0.63
     Administrativna
    0.62
    zerland
    0.61
     ExecuteAsync
    0.61
    INSEE
    0.61
     initWith
    0.60
    RegistryLite
    0.60
    ManagedBean
    0.59
    +:+
    0.59
    Activations Density 0.990%

    No Known Activations