© 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. 18-GEMMASCOPE-RES-16K
    11. 4793
    Prev
    Next
    INDEX
    Explanations

    questions that seek to inform or surprise the reader

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

    Preceding "know" (or similar words)

    np_acts-logits-general · gemini-2.0-flash

    to know

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    mergeFrom
    -0.81
     myſelf
    -0.78
    HideFlags
    -0.77
    رشف
    -0.75
     للمعارف
    -0.74
    IUrlHelper
    -0.72
     <<<<<<<<<<<<<<
    -0.71
    पया
    -0.69
     الحره
    -0.69
     doubtnut
    -0.68
    POSITIVE LOGITS
     know
    1.52
    know
    1.36
    Know
    1.35
     Know
    1.32
     knew
    1.28
    知
    1.25
     knowing
    1.17
    知道
    1.16
     knows
    1.14
    KNOW
    1.10
    Activations Density 0.109%

    No Known Activations