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. 4-GEMMASCOPE-RES-16K
    6. 15963
    Prev
    Next
    INDEX
    Explanations

    terms related to software licenses, specifically the Eclipse license

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.hook_resid_post
    Hook Layer
    4
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     مشين
    -0.72
     nakalista
    -0.62
    fontawesome
    -0.61
    bootstrapcdn
    -0.60
     отношению
    -0.60
    قایناقلار
    -0.58
    FormTagHelper
    -0.58
     toán
    -0.58
    كويكب
    -0.57
    Bibliografie
    -0.57
    POSITIVE LOGITS
    ValueStyle
    0.76
    thenReturn
    0.67
    SBATCH
    0.61
     fossero
    0.60
    plevel
    0.55
     käs
    0.55
    ihnachts
    0.53
     vistos
    0.52
     Flores
    0.52
    views
    0.52
    Activations Density 0.084%

    No Known Activations