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. 7329
    Prev
    Next
    INDEX
    Explanations

    specific types of citations or references, particularly in relation to medical and technical contexts

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

    Text within or abbreviated as parentheses

    np_acts-logits-general · gemini-2.0-flash

    ch/Ch beginnings, abbreviations

    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
    principalTable
    -0.57
    mbggenerated
    -0.48
    caler
    -0.46
    tellbar
    -0.44
    ContentAsync
    -0.44
     lccn
    -0.43
    pielen
    -0.43
    pielt
    -0.43
     Avery
    -0.43
    glGen
    -0.40
    POSITIVE LOGITS
     ch
    1.04
    ch
    1.00
     CH
    0.97
    Ch
    0.96
    CH
    0.96
     chiral
    0.95
     Ch
    0.93
    ACH
    0.90
    chl
    0.89
     Chalmers
    0.89
    Activations Density 0.684%

    No Known Activations