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. 16-GEMMASCOPE-RES-16K
    6. 6218
    Prev
    Next
    INDEX
    Explanations

    elements related to organizations or meetings, especially in political contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    TagMode
    -0.53
    himself
    -0.51
     تانيه
    -0.50
    autre
    -0.49
     yourselves
    -0.49
     heo
    -0.49
    ientôt
    -0.48
     himſelf
    -0.47
     他
    -0.47
    他
    -0.47
    POSITIVE LOGITS
     CEO
    0.84
     Director
    0.78
     Chief
    0.77
     director
    0.74
     Captain
    0.73
    Captain
    0.72
     founder
    0.71
     captain
    0.71
     Superintendent
    0.70
     Başkanı
    0.69
    Activations Density 0.422%

    No Known Activations