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. 9-GEMMASCOPE-RES-16K
    6. 1432
    Prev
    Next
    INDEX
    Explanations

    phrases related to authority and responsibility in leadership contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_9/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    lees
    -0.45
     onBind
    -0.43
    relsen
    -0.42
     faim
    -0.42
     relative
    -0.41
    iyle
    -0.41
     comuni
    -0.40
     research
    -0.39
    Noti
    -0.39
     id
    -0.39
    POSITIVE LOGITS
    WithIOException
    0.73
     @"/
    0.71
    verwijspagina
    0.71
    responsible
    0.71
    Responsibility
    0.70
     takeover
    0.70
    BufferException
    0.68
     übernimmt
    0.68
     übernehmen
    0.68
     ejecut
    0.67
    Activations Density 0.468%

    No Known Activations