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. 21-GEMMASCOPE-RES-16K
    6. 885
    Prev
    Next
    INDEX
    Explanations

    technical specifications and components related to mechanical or electrical devices

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    complexType
    -0.61
    oolean
    -0.57
     confound
    -0.53
    fortawesome
    -0.52
    cloudflare
    -0.51
    şme
    -0.51
    Sidebar
    -0.50
     theme
    -0.50
    LLocation
    -0.50
    徨
    -0.50
    POSITIVE LOGITS
     attached
    1.20
    attached
    1.04
     Attached
    1.01
     attach
    0.97
     attaches
    0.90
    Attached
    0.89
    attach
    0.88
     resting
    0.87
     hanging
    0.85
     protruding
    0.84
    Activations Density 0.810%

    No Known Activations