© 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-2-9B-IT
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 4494
    Prev
    Next
    INDEX
    Explanations

    technical terms related to scientific and medical measurements or processes

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

    Text after a number and a letter

    np_acts-logits-general · gemini-2.0-flash

    postinoculation or postinjection duration

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    +#+#
    -0.75
     <<<<<<<<<<<<<<
    -0.68
    bootstrapcdn
    -0.68
     виправивши
    -0.65
    writeFieldEnd
    -0.64
     himo
    -0.64
    ChildScrollView
    -0.63
     MainAxisSize
    -0.63
     المعيارى
    -0.61
    󠁣
    -0.60
    POSITIVE LOGITS
    ,’”
    0.49
    ​—
    0.48
     neceſſ
    0.47
     neceffary
    0.46
     ſeveral
    0.45
     stället
    0.45
     poffible
    0.45
     Afterward
    0.44
     faſt
    0.44
    strictEqual
    0.43
    Activations Density 2.092%

    No Known Activations