© 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. 19-GEMMASCOPE-RES-16K
    6. 10618
    Prev
    Next
    INDEX
    Explanations

    variations of the prefix "conf" as well as references to configurations and compliance

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 19-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_19/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Hook Layer
    19
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    enterOuterAlt
    -0.66
    Portale
    -0.65
     numberWith
    -0.61
     ESR
    -0.60
     actionPerformed
    -0.60
    Kontrola
    -0.57
     grecque
    -0.56
     grec
    -0.56
    ESR
    -0.56
    enumii
    -0.55
    POSITIVE LOGITS
     conf
    0.87
     Conf
    0.86
     CONF
    0.79
    conf
    0.78
     getConfig
    0.77
    Conf
    0.72
    Configs
    0.68
     Config
    0.68
     Konf
    0.67
    CONF
    0.67
    Activations Density 0.152%

    No Known Activations