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. 12763
    Prev
    Next
    INDEX
    Explanations

    expressions of greeting and introductory phrases

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

    Text following punctuation

    np_acts-logits-general · gemini-2.0-flash

    coding and formal greetings

    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
    <eos>
    -0.75
    zuma
    -0.55
    iral
    -0.47
     clashed
    -0.45
     trattamento
    -0.43
    getLatitude
    -0.43
    StoreMessageInfo
    -0.42
    偏偏
    -0.41
    em
    -0.41
     اضاف
    -0.41
    POSITIVE LOGITS
     Савезне
    0.85
    MigrationBuilder
    0.78
    Greetings
    0.74
     Greetings
    0.72
     greetings
    0.71
    sizeCache
    0.70
     CreateTagHelper
    0.70
    évaluateur
    0.68
    interopRequire
    0.67
    CompilerServices
    0.65
    Activations Density 0.196%

    No Known Activations