© 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. 9644
    Prev
    Next
    INDEX
    Explanations

    URLs and links related to GitHub

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

    Code import statements' forward slashes

    np_acts-logits-general · gemini-2.0-flash

    apex, Azure, go, Foundation, MED, Newsletter

    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
     nakalista
    -0.74
    cookieParser
    -0.61
     disambiguazione
    -0.60
     Toujours
    -0.56
     hini
    -0.56
    disambiguation
    -0.56
    Lähteet
    -0.56
    存于互联网档案馆
    -0.56
     оригіналу
    -0.56
    izr
    -0.55
    POSITIVE LOGITS
    flutter
    0.62
    DrawerToggle
    0.59
    KURZBESCHREIBUNG
    0.58
    ToProps
    0.54
    ipient
    0.52
    Collegamenti
    0.52
    RectangleBorder
    0.51
     ***!
    0.49
     useEffect
    0.48
    жешь
    0.48
    Activations Density 0.016%

    No Known Activations