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. 0-GEMMASCOPE-RES-16K
    6. 6412
    Prev
    Next
    INDEX
    Explanations

    instances of demonstrative pronouns or transitional phrases that introduce or summarize findings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 0-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.hook_resid_post
    Hook Layer
    0
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     виправивши
    -1.28
    expandindo
    -1.18
     disambiguazione
    -1.15
    MessageOf
    -1.10
    AddTagHelper
    -1.04
     المعيارى
    -1.04
    تقاوى
    -1.03
    AndEndTag
    -1.03
     ujednoznacz
    -1.02
     ExecuteAsync
    -1.02
    POSITIVE LOGITS
     The
    1.25
     This
    1.22
     These
    1.11
     It
    1.07
     We
    0.91
     There
    0.84
     You
    0.78
     In
    0.78
     Such
    0.78
     (
    0.77
    Activations Density 0.353%

    No Known Activations