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. 12014
    Prev
    Next
    INDEX
    Explanations

    statements related to sustainability and resource efficiency in product marketing

    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
    er
    -0.80
    たまた
    -0.68
    n
    -0.68
    ing
    -0.67
     last
    -0.67
    r
    -0.66
    t
    -0.64
     where
    -0.63
     back
    -0.62
    p
    -0.61
    POSITIVE LOGITS
     ECR
    0.90
     preſent
    0.89
     ་་
    0.88
    hanger
    0.86
     дописавши
    0.86
     qx
    0.82
     uuidv
    0.82
     myſelf
    0.81
     CURIAM
    0.81
    Celsius
    0.80
    Activations Density 0.046%

    No Known Activations