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. 2939
    Prev
    Next
    INDEX
    Explanations

    instances of physical descriptions or conditions in a narrative context

    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
     ComVisible
    -0.50
     tán
    -0.47
    WEBPACK
    -0.44
    berton
    -0.42
     Sociales
    -0.42
    culares
    -0.41
    PROBE
    -0.41
    setupUi
    -0.41
     udaler
    -0.41
     Domain
    -0.41
    POSITIVE LOGITS
     bed
    2.30
     beds
    1.92
     Bed
    1.81
    Bed
    1.79
    bed
    1.78
     BED
    1.74
     Beds
    1.67
    beds
    1.62
    BED
    1.52
    Beds
    1.52
    Activations Density 0.098%

    No Known Activations