© 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. 0-GEMMASCOPE-RES-16K
    11. 8841
    Prev
    Next
    INDEX
    Explanations

    instances of the word "already," indicating a context of prior actions or decisions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 0-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.hook_resid_post
    Hook Layer
    0
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Савезне
    -1.32
    IntoConstraints
    -1.19
    ſelf
    -1.18
     Efq
    -1.18
    parsedMessage
    -1.15
     itſelf
    -1.15
    DeleteBehavior
    -1.12
     kaarangay
    -1.11
     Forumite
    -1.11
     Мексичка
    -1.11
    POSITIVE LOGITS
    ↵
    0.78
    <eos>
    0.67
     
    0.66
    .
    0.64
    ↵↵
    0.63
     have
    0.63
    has
    0.63
    ve
    0.62
     /
    0.61
    led
    0.58
    Activations Density 0.189%

    No Known Activations