© 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. 6-GEMMASCOPE-RES-16K
    6. 2904
    Prev
    Next
    INDEX
    Explanations

    prepositions and their context in relation to actions or states

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 6-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_6/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.6.hook_resid_post
    Hook Layer
    6
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     تانيه
    -0.69
    PostExecute
    -0.68
    OGND
    -0.60
    HomeAsUpEnabled
    -0.56
     maît
    -0.55
    Zeneca
    -0.55
    erçe
    -0.54
    ajuato
    -0.53
    Xna
    -0.53
     שוליים
    -0.51
    POSITIVE LOGITS
     onto
    0.86
     board
    0.81
    board
    0.76
    boarding
    0.66
    Board
    0.65
     PED
    0.64
     Board
    0.63
     BOARD
    0.62
     aufs
    0.61
     Hov
    0.59
    Activations Density 0.105%

    No Known Activations