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. 5038
    Prev
    Next
    INDEX
    Explanations

    URLs or web links within the text

    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
    ########.
    -1.04
    Tikang
    -1.01
    UserScript
    -0.91
     Catawiki
    -0.89
    TypedDataSet
    -0.87
    GEBURTS
    -0.85
    MLLoader
    -0.83
    NgModule
    -0.83
    :✨
    -0.82
    jsonwebtoken
    -0.81
    POSITIVE LOGITS
     of
    1.06
     to
    0.97
     is
    0.94
     are
    0.82
     for
    0.82
     and
    0.81
     be
    0.79
     has
    0.79
     the
    0.79
     been
    0.78
    Activations Density 0.224%

    No Known Activations