© 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-2-9B
    7. Residual Stream - 16k
    9. 24-GEMMASCOPE-RES-16K
    11. 1417
    Prev
    Next
    INDEX
    Explanations

    references to manual actions and user interactions in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    "manually" or "manual"

    np_acts-logits-general · gemini-2.0-flash

    manual or manually

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_24/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Automatically
    -0.47
    Automatically
    -0.44
    ̍t
    -0.44
     Automatic
    -0.39
    Insee
    -0.37
    Automat
    -0.37
    hallen
    -0.36
     Buff
    -0.36
     Taus
    -0.35
     automatically
    -0.35
    POSITIVE LOGITS
     manually
    0.99
     manual
    0.90
     manualmente
    0.81
    manual
    0.81
     manuell
    0.76
     Manually
    0.73
    手动
    0.73
    Manually
    0.71
    MANUAL
    0.69
     Manual
    0.69
    Activations Density 0.795%

    No Known Activations