© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 18-GEMMASCOPE-RES-16K
    6. 2452
    Prev
    Next
    INDEX
    Explanations

    quantitative financial data and related statistics

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

    Numbers following "tz.transition"

    np_acts-logits-general · gemini-2.0-flash

    numbers and mathematical expressions

    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
     EconPapers
    -0.95
    GEBURTSDATUM
    -0.90
     مشين
    -0.81
     Normdatei
    -0.79
    Geplaatst
    -0.73
    IndentedString
    -0.66
    astify
    -0.65
    hnia
    -0.64
     SafeMath
    -0.64
     ampoule
    -0.64
    POSITIVE LOGITS
     Genshin
    0.59
    ordning
    0.47
    venti
    0.45
     kiếm
    0.45
    blå
    0.45
    蛍
    0.44
     commerciaux
    0.42
     libri
    0.42
     insectes
    0.42
     commerciales
    0.41
    Activations Density 0.139%

    No Known Activations