© 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. 4-GEMMASCOPE-RES-16K
    11. 11795
    Prev
    Next
    INDEX
    Explanations

    punctuation marks and sentence endings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.hook_resid_post
    Hook Layer
    4
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ReusableCell
    -0.82
    EFIAPI
    -0.82
    \}_{
    -0.82
    Билгалдахарш
    -0.81
     Chwiliwch
    -0.81
    ⓧ
    -0.81
    onedDateTime
    -0.81
    tvguidetime
    -0.80
     utafitiHapana
    -0.79
    odotus
    -0.79
    POSITIVE LOGITS
    .
    1.20
    ).
    0.94
    ↵↵
    0.94
     The
    0.85
     This
    0.84
     Although
    0.83
    <bos>
    0.83
    。
    0.79
     However
    0.79
     If
    0.78
    Activations Density 2.395%

    No Known Activations