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. 16-GEMMASCOPE-RES-16K
    6. 3004
    Prev
    Next
    INDEX
    Explanations

    sections of the text that contain specific operational or procedural instructions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Text before/after code or markup tags

    np_acts-logits-general · gemini-2.0-flash

    when or as followed by a specific word

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    degna
    -0.54
     "..\..\..\
    -0.54
    enaars
    -0.52
     Wikimedijinoj
    -0.52
    ⭒
    -0.51
    EndGlobalSection
    -0.50
     Lindberg
    -0.48
     ändå
    -0.47
     certainly
    -0.46
    istisches
    -0.45
    POSITIVE LOGITS
     BoxDecoration
    0.67
    RegressionTest
    0.63
     endwhile
    0.61
    IsContent
    0.59
     getopt
    0.59
    ArgumentParser
    0.59
    THISDAY
    0.59
    IonicModule
    0.55
    ουσ
    0.54
    runApp
    0.54
    Activations Density 0.074%

    No Known Activations