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. 1988
    Prev
    Next
    INDEX
    Explanations

    references to scientific names and terms related to nanotechnology and notable figures in science

    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
    featureID
    -1.18
     lenker
    -1.01
    AnchorStyles
    -0.99
    ########.
    -0.90
     []:
    -0.85
     Schlä
    -0.83
     Budi
    -0.80
     nahilalakip
    -0.78
    WebMethod
    -0.78
     Hars
    -0.78
    POSITIVE LOGITS
    ration
    0.76
    ceans
    0.74
     omicron
    0.73
     Davison
    0.71
     Kidd
    0.70
     Layton
    0.69
     Coleridge
    0.67
    ilions
    0.66
    らう
    0.66
    edenken
    0.65
    Activations Density 3.744%

    No Known Activations