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. 9337
    Prev
    Next
    INDEX
    Explanations

    pronouns, particularly "you"

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

    Follows "you" with "know" or a similar word

    np_acts-logits-general · gemini-2.0-flash

    you know

    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
     Normdatei
    -0.74
    niająca
    -0.71
    ⓧ
    -0.63
    PMailer
    -0.63
    piac
    -0.60
     typelib
    -0.58
     oublié
    -0.58
    parsedMessage
    -0.58
    +:+
    -0.58
    CodedInputStream
    -0.58
    POSITIVE LOGITS
     know
    1.52
    know
    1.25
     Know
    1.10
    Know
    0.98
     knows
    0.97
    KNOW
    0.89
     KNOW
    0.88
     sabes
    0.84
    你知道
    0.83
     known
    0.80
    Activations Density 0.079%

    No Known Activations