© 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. 22-GEMMASCOPE-RES-16K
    11. 8520
    Prev
    Next
    INDEX
    Explanations

    words with specific phonetic patterns or suffixes

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

    ending in "en," "den," "len," "uen."

    np_acts-logits-general · gemini-2.0-flash

    words ending in "en"

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     CreateTagHelper
    -0.80
    ActionCreators
    -0.71
    tance
    -0.70
    mapStateToProps
    -0.67
    DataAnnotations
    -0.64
    damente
    -0.64
    MeasureSpec
    -0.64
    toHaveBeenCalled
    -0.63
    schild
    -0.62
    RegistryLite
    -0.62
    POSITIVE LOGITS
    ning
    0.71
    ek
    0.64
    na
    0.61
    ext
    0.60
    ews
    0.59
    ey
    0.59
    ny
    0.57
    ew
    0.55
    nen
    0.54
    ne
    0.54
    Activations Density 0.335%

    No Known Activations