© 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. 6318
    Prev
    Next
    INDEX
    Explanations

    patterns or structures in data representations

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

    Filenames or URLs with hyphens

    np_acts-logits-general · gemini-2.0-flash

    structural separators

    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
    +#+#
    -0.53
     myſelf
    -0.52
     juſ
    -0.52
    Tembelea
    -0.50
    帖最后由
    -0.50
     pleaſure
    -0.47
    AxisAlignment
    -0.47
     Naciones
    -0.46
     useAuth
    -0.45
     setEmail
    -0.44
    POSITIVE LOGITS
    GEBURTSDATUM
    0.62
    ніципа
    0.52
    _
    0.47
    #
    0.45
    aby
    0.43
    addCriterion
    0.41
     ved
    0.41
    TALL
    0.40
    GREG
    0.40
    CodeAttribute
    0.40
    Activations Density 0.115%

    No Known Activations