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. 725
    Prev
    Next
    INDEX
    Explanations

    verbs and actions related to giving, sending, and loans

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    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
    tagHelperRunner
    -0.57
    AndEndTag
    -0.57
    TintMode
    -0.54
    DoubleQuotes
    -0.52
    gians
    -0.51
     ProtoMessage
    -0.48
    schirm
    -0.47
    Попис
    -0.47
    yntaxException
    -0.47
    }{*}{}
    -0.47
    POSITIVE LOGITS
     meille
    1.21
     ему
    1.11
     ей
    1.01
     нам
    0.99
     вам
    0.96
    argli
    0.94
     us
    0.94
     Ihnen
    0.88
     мне
    0.87
     me
    0.85
    Activations Density 0.180%

    No Known Activations