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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 3-GEMMASCOPE-RES-16K
    6. 9015
    Prev
    Next
    INDEX
    Explanations

    references to specific individuals and their performances in a sports context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    COUVER
    -0.51
     siglas
    -0.45
    shooting
    -0.45
     Unies
    -0.44
     generales
    -0.44
     ê
    -0.43
     abordagem
    -0.43
    詳しい
    -0.42
     exatamente
    -0.42
     gesteld
    -0.42
    POSITIVE LOGITS
    titleMargin
    0.78
     Económica
    0.70
    istoitu
    0.70
     chi̍t
    0.69
     ComVisible
    0.69
     Monfieur
    0.69
     BoxDecoration
    0.68
     nahilalakip
    0.67
    CppMethod
    0.66
     myſelf
    0.65
    Activations Density 0.708%

    No Known Activations