© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 1-GEMMASCOPE-RES-16K
    11. 5700
    Prev
    Next
    INDEX
    Explanations

    repeated instances of the word "and."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.1.hook_resid_post
    Hook Layer
    1
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     and
    -0.93
    ,
    -0.65
    .
    -0.51
    ↵
    -0.45
    いざ
    -0.40
     térmica
    -0.39
    <eos>
    -0.35
     koul
    -0.34
    -
    -0.33
     &
    -0.33
    POSITIVE LOGITS
     مشين
    1.14
     تضيفلها
    1.07
    DeleteBehavior
    1.04
    parsedMessage
    0.99
     Chwiliwch
    0.98
    Personensuche
    0.97
    躇
    0.96
    CppMethod
    0.96
    脚注の使い方
    0.92
    jsxFileName
    0.91
    Activations Density 0.260%

    No Known Activations