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. 3239
    Prev
    Next
    INDEX
    Explanations

    special characters and syntax commonly used in programming code

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

    Code file paths or URLs

    np_acts-logits-general · gemini-2.0-flash

    code identifiers and library 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
     nakalista
    -0.53
     breeches
    -0.51
     Theod
    -0.47
    KommentareTeilen
    -0.47
    lossians
    -0.46
     kysy
    -0.45
     mills
    -0.44
    ParallelGroup
    -0.44
     drill
    -0.43
     seção
    -0.43
    POSITIVE LOGITS
     resourceCulture
    0.79
    GOTREF
    0.76
    PerformLayout
    0.73
    ConstraintMaker
    0.70
    存于互联网档案馆
    0.70
    adaptiveStyles
    0.63
    Aholisi
    0.61
     GenerationType
    0.59
    BeginContext
    0.59
    parseFrom
    0.59
    Activations Density 0.068%

    No Known Activations