© 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. 19-GEMMASCOPE-RES-16K
    6. 1648
    Prev
    Next
    INDEX
    Explanations

    references to licensing and supplementary materials

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 19-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_19/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Hook Layer
    19
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Normdatei
    -0.84
    :✨
    -0.78
    parsedMessage
    -0.76
    findpost
    -0.76
    aarrggbb
    -0.75
     EconPapers
    -0.74
     nakalista
    -0.73
     resourceCulture
    -0.71
    DataAnnotations
    -0.71
    IsPostBack
    -0.71
    POSITIVE LOGITS
     for
    2.25
    for
    1.44
     для
    1.40
     untuk
    1.39
     voor
    1.29
     برای
    1.23
     für
    1.18
     pentru
    1.14
     για
    1.13
    สำหรับ
    1.07
    Activations Density 0.378%

    No Known Activations