Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & 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. 10-GEMMASCOPE-RES-16K
    6. 12633
    Prev
    Next
    INDEX
    Explanations

    terms related to rarity or exceptional occurrences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ItemBackground
    -0.74
     <<<<<<<<<<<<<<
    -0.74
    NewUrlParser
    -0.66
    󠁢
    -0.65
    surate
    -0.64
    }{*}{
    -0.63
    ropriate
    -0.62
     springfox
    -0.60
    titleMargin
    -0.60
    astéroïdes
    -0.60
    POSITIVE LOGITS
     rare
    1.28
    rare
    1.06
     Rare
    1.05
    Rare
    1.01
     rarity
    0.99
     rarest
    0.92
     raro
    0.91
     RARE
    0.90
     rares
    0.89
     raras
    0.89
    Activations Density 0.317%

    No Known Activations