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. 5-GEMMASCOPE-RES-16K
    6. 12841
    Prev
    Next
    INDEX
    Explanations

    references to institutions, organizations, and formal titles related to governance and academia

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ThroughAttribute
    -0.67
    verifyException
    -0.64
    tako
    -0.59
     køb
    -0.56
    entennial
    -0.55
    راسیون
    -0.54
    tilhe
    -0.51
    tagHelperRunner
    -0.51
    んでしょう
    -0.51
    万美元
    -0.50
    POSITIVE LOGITS
     Brexit
    1.07
     Britons
    1.04
     LONDON
    1.01
    London
    1.00
     London
    1.00
     UK
    0.99
     British
    0.97
    -£
    0.97
     Britain
    0.94
    Brexit
    0.94
    Activations Density 1.429%

    No Known Activations