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. 2964
    Prev
    Next
    INDEX
    Explanations

    phrases that indicate relationships or connections involving the concept of "to" and associated actions

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

    Question words after prepositions

    np_acts-logits-general · gemini-2.0-flash

    questions starting with prepositions like 'what'

    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
     HasFactory
    -0.67
    SharedCtor
    -0.59
    uxxxx
    -0.55
     noqa
    -0.53
     getItemId
    -0.50
    interopRequire
    -0.50
    !*\
    -0.49
    maxcdn
    -0.49
     hefyd
    -0.48
    bury
    -0.47
    POSITIVE LOGITS
     what
    2.56
    what
    2.17
     how
    1.91
     WHAT
    1.90
     What
    1.90
    What
    1.86
    WHAT
    1.68
     qué
    1.55
     whats
    1.51
     why
    1.51
    Activations Density 0.398%

    No Known Activations