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. 10725
    Prev
    Next
    INDEX
    Explanations

    references to individuals with the title "Mr." followed by a name

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

    "Mr" preceding a name

    np_acts-logits-general · gemini-2.0-flash

    Mr followed by name

    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
    findpost
    -0.51
    ecap
    -0.47
    形で
    -0.45
    timento
    -0.44
     aldrig
    -0.44
    ZoneId
    -0.43
     Strafe
    -0.43
    sweetalert
    -0.43
     argparse
    -0.43
    eml
    -0.43
    POSITIVE LOGITS
    fjspx
    0.72
     DBNull
    0.66
    ModelSerializer
    0.64
     CGRectMake
    0.63
     President
    0.62
    帖最后由
    0.62
     yyl
    0.61
     protoimpl
    0.61
     iVar
    0.60
     kaarangay
    0.60
    Activations Density 0.069%

    No Known Activations