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. 10146
    Prev
    Next
    INDEX
    Explanations

    specific HTML tags and their attributes typically associated with web development

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

    Text containing special characters or markup

    np_acts-logits-general · gemini-2.0-flash

    Unity/script files

    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
     виправивши
    -0.53
     uova
    -0.44
    princ
    -0.43
    ReusableCell
    -0.42
     époque
    -0.42
    win
    -0.42
     zucchero
    -0.41
     cucchia
    -0.41
     redor
    -0.41
     <<<<<<<<<<<<<<
    -0.41
    POSITIVE LOGITS
    InjectAttribute
    1.01
    TagMode
    0.92
    istoitu
    0.86
     beginnetje
    0.79
     nahilalakip
    0.77
     surla
    0.73
     doInBackground
    0.72
    onames
    0.72
    uxxxx
    0.71
     Bourgoin
    0.70
    Activations Density 0.027%

    No Known Activations