© 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. 10-GEMMASCOPE-RES-16K
    11. 13484
    Prev
    Next
    INDEX
    Explanations

    sentences or phrases that express conditional situations or hypothetical statements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Jefus
    -0.70
    Portale
    -0.70
     Numerade
    -0.69
     Diſ
    -0.67
     houſe
    -0.65
     Anſ
    -0.64
     ſtate
    -0.62
     ſame
    -0.60
    QtCore
    -0.60
    weiler
    -0.59
    POSITIVE LOGITS
     which
    0.85
     whose
    0.84
     الحره
    0.84
     that
    0.83
    SourceChecksum
    0.79
    pidou
    0.75
    /******/
    0.73
     who
    0.72
     متعلقه
    0.72
     whom
    0.71
    Activations Density 0.061%

    No Known Activations