© 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. 12-GEMMASCOPE-RES-16K
    6. 11157
    Prev
    Next
    INDEX
    Explanations

    phrases that indicate the presence of the word "with" followed closely by other significant words or phrases

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ogóle
    -0.61
     refirió
    -0.56
     kenapa
    -0.56
    tų
    -0.55
    UnknownFieldSet
    -0.55
     verbatim
    -0.54
    parsedMessage
    -0.54
     magát
    -0.54
    omiast
    -0.54
     mesmas
    -0.53
    POSITIVE LOGITS
     With
    0.86
    With
    0.81
    有了
    0.77
    ostante
    0.70
     knowing
    0.67
    enumeration
    0.63
    Με
    0.63
     ligiloj
    0.62
     Having
    0.61
     hindsight
    0.61
    Activations Density 0.065%

    No Known Activations