© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 8-GEMMASCOPE-RES-16K
    6. 11518
    Prev
    Next
    INDEX
    Explanations

    the word "scheme" and its variations used in a mathematical or algorithmic context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 8-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_8/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.hook_resid_post
    Hook Layer
    8
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     poffible
    -0.83
     poffe
    -0.77
     EAT
    -0.72
    fist
    -0.71
    »»
    -0.71
     Efq
    -0.70
     Horton
    -0.69
     محفوظة
    -0.69
    iteness
    -0.69
    registrer
    -0.69
    POSITIVE LOGITS
     SCHEME
    1.86
    Scheme
    1.82
     scheme
    1.80
     schemes
    1.77
    scheme
    1.77
     Scheme
    1.75
     Schemes
    1.73
    SCHEME
    1.69
    schemes
    1.68
    cheme
    1.61
    Activations Density 0.084%

    No Known Activations