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. 0-GEMMASCOPE-RES-16K
    6. 133
    Prev
    Next
    INDEX
    Explanations

    references to poverty and related themes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 0-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.hook_resid_post
    Hook Layer
    0
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     myſelf
    -3.52
     itſelf
    -3.48
     Efq
    -3.27
     Jefus
    -3.19
     Theſe
    -3.17
    ſelf
    -3.09
     purpoſe
    -3.08
     Monfieur
    -3.06
     Majefty
    -2.99
     ſeveral
    -2.97
    POSITIVE LOGITS
    ,
    1.98
    .
    1.86
     (
    1.85
     
    1.80
     in
    1.63
    :
    1.57
     and
    1.55
    !
    1.50
    ↵
    1.49
     for
    1.48
    Activations Density 0.226%

    No Known Activations