© 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-2-9B
    4. Residual Stream - 16k
    5. 41-GEMMASCOPE-RES-16K
    6. 6448
    Prev
    Next
    INDEX
    Explanations

    LaTeX commands and formatting related to mathematical or scientific content

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 41-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_41/width_16k/average_l0_113
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.41.hook_resid_post
    Hook Layer
    41
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    writeFieldEnd
    -0.79
    脚注の使い方
    -0.76
    RTLR
    -0.68
     kasarigan
    -0.66
    StructEnd
    -0.65
    ContentAsync
    -0.65
    PullParser
    -0.64
    setVerticalGroup
    -0.64
    Дереккөздер
    -0.63
    RTLI
    -0.63
    POSITIVE LOGITS
     Comunicação
    0.34
    hline
    0.30
     Bakterien
    0.25
     públicas
    0.25
    substack
    0.24
    oa̍t
    0.23
     normalidad
    0.23
     нас
    0.22
     peito
    0.22
     puteți
    0.22
    Activations Density 0.053%

    No Known Activations