Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit 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. 5-GEMMASCOPE-RES-16K
    6. 9996
    Prev
    Next
    INDEX
    Explanations

    information related to product availability and promotions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     AssemblyCompany
    -1.04
     StatefulWidget
    -0.98
     StatelessWidget
    -0.98
     HasFactory
    -0.97
     EconPapers
    -0.94
    \{\\
    -0.90
     дописавши
    -0.90
    tvguidetime
    -0.89
    InjectAttribute
    -0.86
    出版年
    -0.86
    POSITIVE LOGITS
     --
    0.47
     "
    0.43
     
    0.43
    <sup>
    0.43
     —
    0.42
     (
    0.40
     –
    0.40
     integrated
    0.38
    __
    0.37
    <sub>
    0.35
    Activations Density 0.386%

    No Known Activations