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. 2081
    Prev
    Next
    INDEX
    Explanations

    expressions of confusion or uncertainty related to personal choices and societal expectations

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

    Reflexive pronouns and possessive adjectives

    np_acts-logits-general · gemini-2.0-flash

    possessive pronouns and themselves

    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
    contentLoaded
    -0.66
     nostru
    -0.60
    felf
    -0.60
     myſelf
    -0.56
    AddHtmlAttribute
    -0.55
     itſelf
    -0.53
     själv
    -0.51
    Tracce
    -0.50
     noastră
    -0.50
    antMatchers
    -0.49
    POSITIVE LOGITS
     their
    3.26
     themselves
    3.07
    Their
    2.95
    their
    2.80
     Their
    2.74
    themselves
    2.57
     THEIR
    2.20
     leurs
    2.03
     ihre
    2.02
    他们的
    1.95
    Activations Density 3.618%

    No Known Activations