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-2-9B-IT
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 909
    Prev
    Next
    INDEX
    Explanations

    phrases related to contributions, skills, and the value of diversity in teams or workplaces

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

    following certain verbs or adjectives

    np_acts-logits-general · gemini-2.0-flash

    contribution, asset, population, absence, force

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91
    Prompts (Dashboard)
    24,576 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
    LookAnd
    -0.38
    kozások
    -0.35
    extAlignment
    -0.34
    ום
    -0.34
     Publish
    -0.34
     published
    -0.33
    serviceWorker
    -0.33
    siones
    -0.33
     publish
    -0.33
     Administrativna
    -0.32
    POSITIVE LOGITS
     nonUne
    0.54
    Personendaten
    0.53
     aporta
    0.53
    StoryboardSegue
    0.51
    bootstrapcdn
    0.50
    experienced
    0.50
    TagMode
    0.49
    новништво
    0.48
    adaptiveStyles
    0.48
     AppComponent
    0.46
    Activations Density 0.344%

    No Known Activations