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. 22-GEMMASCOPE-RES-16K
    6. 14088
    Prev
    Next
    INDEX
    Explanations

    architectural features and design elements in descriptions of spaces

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     فريبيس
    -0.78
    niająca
    -0.68
     houſe
    -0.67
     Houſe
    -0.67
     Jefus
    -0.66
     Wiktionnaire
    -0.65
     pauv
    -0.63
     âges
    -0.63
     Anſ
    -0.63
    IntoConstraints
    -0.63
    POSITIVE LOGITS
     custom
    1.06
     bespoke
    0.87
    custom
    0.85
    Custom
    0.81
     Custom
    0.79
     CUSTOM
    0.70
    CUSTOM
    0.68
     customized
    0.65
     marble
    0.63
     customised
    0.61
    Activations Density 0.052%

    No Known Activations