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. 20-GEMMASCOPE-RES-16K
    6. 8721
    Prev
    Next
    INDEX
    Explanations

    structured data types and programming elements in a technical context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    OGND
    -0.68
     tartalomajánló
    -0.62
     }}^{
    -0.54
    :</
    -0.51
    :\/\/
    -0.51
    \%,
    -0.50
    {}/
    -0.49
     }}(\
    -0.49
    ingway
    -0.49
    **
    
    -0.49
    POSITIVE LOGITS
    .
    1.59
    DeleteBehavior
    0.66
     GenerationType
    0.65
    .,
    0.63
    .(
    0.62
    ._
    0.61
    cdot
    0.58
    .@
    0.57
    ./
    0.57
    providedIn
    0.57
    Activations Density 0.564%

    No Known Activations