© 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. 8937
    Prev
    Next
    INDEX
    Explanations

    words indicating uncertainty or ease regarding situations or actions

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

    Comes before "to"

    np_acts-logits-general · gemini-2.0-flash

    necessary to distinguish

    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
    ίναι
    -0.66
     autorytatywna
    -0.62
    webElementGuid
    -0.59
    Glej
    -0.58
    </caption>
    -0.57
     Abbé
    -0.56
    IVEREF
    -0.56
    loài
    -0.55
     './../
    -0.55
    typeorm
    -0.54
    POSITIVE LOGITS
     geworden
    0.59
     للاسماء
    0.51
    rungsseite
    0.51
     bagi
    0.50
     that
    0.47
    談社
    0.47
    >{@
    0.47
    InputTagHelper
    0.47
     BorderSide
    0.46
    tagext
    0.46
    Activations Density 0.192%

    No Known Activations