© 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. 21-GEMMASCOPE-RES-16K
    11. 15844
    Prev
    Next
    INDEX
    Explanations

    closing braces in code structures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     فريبيس
    -0.90
    aarrggbb
    -0.89
     Administrativna
    -0.89
    PreferredItem
    -0.89
    WithIOException
    -0.86
     חיצוניים
    -0.86
    featureID
    -0.85
     للمعارف
    -0.84
     GenerationType
    -0.83
     autorytatywna
    -0.82
    POSITIVE LOGITS
    le
    0.53
    u
    0.47
    an
    0.42
     un
    0.42
    yn
    0.41
    {{/
    0.41
    ho
    0.41
    -
    0.40
    un
    0.39
    de
    0.38
    Activations Density 0.054%

    No Known Activations