© 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. 4036
    Prev
    Next
    INDEX
    Explanations

    the beginning of new sections or thoughts in a text

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

    before citations or references

    np_acts-logits-general · gemini-2.0-flash

    This The

    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
    -------
    -0.72
     betweenstory
    -0.63
    calaure
    -0.58
    UrlResolution
    -0.57
    findOrFail
    -0.57
    owatt
    -0.56
    RegressionTest
    -0.56
    dì
    -0.54
    bhan
    -0.54
    odori
    -0.54
    POSITIVE LOGITS
     disambiguazione
    0.84
     nahilalakip
    0.83
     autorytatywna
    0.80
    :✨
    0.79
    Autoritní
    0.79
    principalColumn
    0.78
     Roskov
    0.77
    awtextra
    0.75
     chi̍t
    0.74
     مُعرِّف
    0.74
    Activations Density 0.152%

    No Known Activations