© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 2-GEMMASCOPE-RES-16K
    11. 3306
    Prev
    Next
    INDEX
    Explanations

    references to collective action and responsibility among groups or individuals

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Qualquer
    -0.59
     Theſe
    -0.55
     adicionais
    -0.55
     Efq
    -0.51
    TagMode
    -0.51
     Beſ
    -0.50
    Плюсы
    -0.49
     strictest
    -0.48
    aarrggbb
    -0.48
    Autoritní
    -0.46
    POSITIVE LOGITS
    IsContent
    0.69
    utsu
    0.67
    VersionUID
    0.67
    GOTREF
    0.66
    RegistryLite
    0.66
    脚注の使い方
    0.65
     they
    0.64
    GraphicsUnit
    0.64
    GHIJKLM
    0.63
     utafitiHapana
    0.62
    Activations Density 0.613%

    No Known Activations