© 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. 11-GEMMASCOPE-RES-16K
    11. 4450
    Prev
    Next
    INDEX
    Explanations

    symbols and formatting in text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Hook Layer
    11
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Personendaten
    -1.15
    featureID
    -1.01
    mybatisplus
    -0.98
     صوتيه
    -0.96
     ProtoMessage
    -0.95
     disambiguazione
    -0.93
     فريبيس
    -0.92
     NSCoder
    -0.90
     Paglinawan
    -0.89
    Демографія
    -0.88
    POSITIVE LOGITS
    ><
    0.94
    <
    0.92
    <table>
    0.76
    tabular
    0.72
    <!--<
    0.71
    <tr>
    0.68
    "><
    0.68
     <
    0.65
    ="#"><
    0.63
    ."<
    0.63
    Activations Density 0.092%

    No Known Activations