Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 22-GEMMASCOPE-RES-16K
    6. 3302
    Prev
    Next
    INDEX
    Explanations

    phrases related to organizational structures and professional affiliations

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

    Follows "of," "The," or "the" referring to associations/organizations

    np_acts-logits-general · gemini-2.0-flash

    American professional associations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Réponses
    -0.43
     cerró
    -0.41
     softly
    -0.39
    AddTagHelper
    -0.38
    indir
    -0.38
    MathML
    -0.38
    badlogic
    -0.37
     flavoured
    -0.37
     privatisation
    -0.37
    bandcamp
    -0.37
    POSITIVE LOGITS
     professional
    0.90
     membership
    0.89
     profession
    0.88
     association
    0.85
     American
    0.84
    profession
    0.84
     society
    0.82
     Association
    0.82
     Professional
    0.81
     convention
    0.81
    Activations Density 0.297%

    No Known Activations