© 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. 24-GEMMASCOPE-RES-16K
    6. 8943
    Prev
    Next
    INDEX
    Explanations

    variations of the word "gr."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Tokens starting with "Gr"

    np_acts-logits-general · gemini-2.0-flash

    words starting with gr

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_24/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.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     EClass
    -0.71
    NewUrlParser
    -0.69
    Дереккөздер
    -0.59
    AndEndTag
    -0.59
     trattano
    -0.57
    вгения
    -0.57
    ArgsConstructor
    -0.56
    TargetException
    -0.56
    PerformLayout
    -0.53
    اریخ
    -0.52
    POSITIVE LOGITS
     Gri
    0.58
    はじめに
    0.58
     Gr
    0.57
     gr
    0.57
    Gr
    0.55
     GR
    0.54
    Gri
    0.53
    AutoScaleMode
    0.53
     Parlamento
    0.51
     Little
    0.51
    Activations Density 0.153%

    No Known Activations