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. 10177
    Prev
    Next
    INDEX
    Explanations

    instances of the word "for" and its variations indicating duration or quantity

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

    Time period/duration after "for"

    np_acts-logits-general · gemini-2.0-flash

    for + time or quantity

    np_acts-logits-general · gemini-2.5-flash-lite
    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
    
    -0.76
    qrstuvwxyz
    -0.65
    enumi
    -0.64
    ingabe
    -0.64
    IonicModule
    -0.64
     оригіналу
    -0.64
    исленность
    -0.64
    HasForeignKey
    -0.63
    SequentialGroup
    -0.63
     hObject
    -0.63
    POSITIVE LOGITS
     several
    0.69
     brief
    0.64
     nearly
    0.62
     awhile
    0.61
     periods
    0.58
     almost
    0.57
     briefly
    0.55
    大部分
    0.53
     hours
    0.53
    مصادر
    0.52
    Activations Density 0.186%

    No Known Activations