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. 10734
    Prev
    Next
    INDEX
    Explanations

    references to the pronoun "you" and its associated questions about identity or experience

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

    Questions starting with "do you"

    np_acts-logits-general · gemini-2.0-flash

    asking 'do you' questions

    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
     might
    -0.59
     may
    -0.56
    can
    -0.54
     will
    -0.52
    might
    -0.51
     could
    -0.50
     can
    -0.49
     would
    -0.47
     has
    -0.47
    could
    -0.44
    POSITIVE LOGITS
    UserScript
    1.08
     initComponents
    0.92
     ModelExpression
    0.88
     endblock
    0.85
     يتيمه
    0.85
    localctx
    0.81
    .*")]
    0.78
     IndexPath
    0.78
    LikeLiked
    0.77
    migrationBuilder
    0.76
    Activations Density 0.108%

    No Known Activations