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. 21-GEMMASCOPE-RES-16K
    6. 683
    Prev
    Next
    INDEX
    Explanations

    conjunctions and linking phrases in complex sentences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    sizeCache
    -0.85
    fjspx
    -0.83
     BnF
    -0.74
     henceforth
    -0.71
    AndEndTag
    -0.68
    Vidite
    -0.68
     fince
    -0.63
     AssemblyCulture
    -0.62
     dieß
    -0.62
    principalTable
    -0.62
    POSITIVE LOGITS
     plenty
    1.70
     lots
    1.65
     ample
    1.29
     tons
    1.23
     LOTS
    1.22
    lots
    1.22
     Lots
    1.21
     great
    1.19
     excellent
    1.19
    plenty
    1.19
    Activations Density 0.361%

    No Known Activations