© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 16-GEMMASCOPE-RES-16K
    11. 8526
    Prev
    Next
    INDEX
    Explanations

    the beginning of a document or section

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

    Start of code or documentation snippets

    np_acts-logits-general · gemini-2.0-flash

    parenthetical information

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    φαν
    -0.56
     institution
    -0.52
     ((*
    -0.52
     institutional
    -0.52
    териалы
    -0.50
    appar
    -0.50
     conservé
    -0.50
    institution
    -0.49
    anstalt
    -0.49
    breviation
    -0.49
    POSITIVE LOGITS
     officiating
    0.82
    InjectAttribute
    0.80
    UrlResolution
    0.79
     typelib
    0.74
    #+#
    0.73
    ंदीखरीदारी
    0.71
    StructEnd
    0.71
    WriteBarrier
    0.70
    RectangleBorder
    0.70
     pinulongan
    0.67
    Activations Density 0.025%

    No Known Activations