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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 2839
    Prev
    Next
    INDEX
    Explanations

    common conjunctions and transitional phrases that connect ideas in a text

    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
    Hentet
    -0.83
    MLLoader
    -0.64
    cellona
    -0.64
    odiment
    -0.62
     Autorizaciones
    -0.61
    sinon
    -0.59
     SafeMath
    -0.57
    endamento
    -0.57
     Bourgoin
    -0.57
     seguinte
    -0.56
    POSITIVE LOGITS
    enumi
    0.63
    at
    0.62
    ParallelGroup
    0.60
     يتيمه
    0.59
     ostavi
    0.59
    aka
    0.58
    indest
    0.57
    Див
    0.57
    tably
    0.57
    ExtendWith
    0.56
    Activations Density 0.366%

    No Known Activations