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. 6430
    Prev
    Next
    INDEX
    Explanations

    financial reporting and disclosures related to corporate performance and strategy

    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
    Lähteet
    -0.72
    Somehow
    -0.59
     Whatever
    -0.58
     Правда
    -0.58
     Somehow
    -0.57
    ickt
    -0.57
     huge
    -0.56
     nakalista
    -0.56
    Whatever
    -0.55
     convince
    -0.53
    POSITIVE LOGITS
     pursuant
    0.85
     fubject
    0.74
     thereto
    0.70
     approximately
    0.69
     ejus
    0.69
     Majefty
    0.68
     Pursuant
    0.68
     purpoſe
    0.67
     substantially
    0.64
     occafion
    0.62
    Activations Density 0.337%

    No Known Activations