Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 5185
    Prev
    Next
    INDEX
    Explanations

    specific programming-related content and references

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

    Followed by unusual punctuation or capitalization

    np_acts-logits-general · gemini-2.0-flash

    chemical compounds and place names

    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
    
    -0.58
     Seeder
    -0.55
    kháu
    -0.53
    iography
    -0.47
    :✨
    -0.47
    脚注の使い方
    -0.46
    FetchType
    -0.44
    tuvo
    -0.44
     برانيه
    -0.44
    CodeAttribute
    -0.43
    POSITIVE LOGITS
    évaluateur
    0.65
    oshiba
    0.63
    ActivityCompat
    0.60
    protoc
    0.60
    AlterField
    0.59
    baomidou
    0.58
    Gambas
    0.58
    دانشنامهٔ
    0.58
    artifactId
    0.55
     Fairchild
    0.55
    Activations Density 0.012%

    No Known Activations