© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 994
    Prev
    Next
    INDEX
    Explanations

    the possessive form of "is" or "are" in varied contexts

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

    Follows "What's" or "What’s"

    np_acts-logits-general · gemini-2.0-flash

    What's followed by a word

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 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
    BagConstraints
    -0.59
     تضيفلها
    -0.58
    Pfalz
    -0.58
    Either
    -0.54
     nowhere
    -0.53
     Gallimard
    -0.53
    paksa
    -0.52
     Numerade
    -0.51
    awtextra
    -0.50
    Eloquent
    -0.50
    POSITIVE LOGITS
     wrong
    0.87
     causing
    0.69
     required
    0.69
     المعيارى
    0.68
     best
    0.67
    wrong
    0.67
     missing
    0.66
    DispatchToProps
    0.65
    msgSender
    0.65
     happening
    0.65
    Activations Density 0.120%

    No Known Activations