© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 9-GEMMASCOPE-RES-16K
    11. 2421
    Prev
    Next
    INDEX
    Explanations

    the structure of a written document, particularly indicating the beginning and specific sections within it

    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
     pinulongan
    -0.60
    uxxxx
    -0.55
    ArgsConstructor
    -0.53
    市镇
    -0.53
     Clos
    -0.52
    owieck
    -0.49
    ിച്ച
    -0.49
    ionario
    -0.49
    :✨
    -0.49
    tagHelper
    -0.48
    POSITIVE LOGITS
     audience
    0.98
     audiences
    0.95
    Audience
    0.88
    audience
    0.87
     readership
    0.80
     Audience
    0.79
    Audiences
    0.77
     viewers
    0.72
     demographic
    0.71
     millions
    0.66
    Activations Density 0.335%

    No Known Activations