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. 16059
    Prev
    Next
    INDEX
    Explanations

    instances of public commentary and expressions of frustration or surprise

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

    Follows periods or quotation marks

    np_acts-logits-general · gemini-2.0-flash

    specific proper nouns and technical terms

    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
    DebuggerNonUser
    -0.53
    onAttach
    -0.52
    forderung
    -0.48
    jsonwebtoken
    -0.44
     again
    -0.44
     gu
    -0.43
    кому
    -0.43
    ่านั้น
    -0.43
    modelName
    -0.41
    عنی
    -0.41
    POSITIVE LOGITS
     EconPapers
    0.76
     Walkover
    0.74
    RegistryLite
    0.68
     Egli
    0.63
     egli
    0.62
     saites
    0.62
    他是
    0.57
    ագրություններ
    0.57
     littéraire
    0.56
    RenderAtEndOf
    0.56
    Activations Density 0.206%

    No Known Activations