© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 797
    Prev
    Next
    INDEX
    Explanations

    functional programming patterns such as mapping and chaining operations

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

    JavaScript array iteration methods

    np_acts-logits-general · gemini-2.0-flash

    javascript array methods

    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
     متعلقه
    -0.87
    parsedMessage
    -0.83
     tartalomajánló
    -0.79
    LookAnd
    -0.76
     Италијани
    -0.75
     Reſ
    -0.75
     purpoſe
    -0.75
    /**
    -0.73
     estekak
    -0.73
     perſon
    -0.71
    POSITIVE LOGITS
    ((
    0.60
    (({
    0.49
    (()
    0.48
    imide
    0.44
    ilanth
    0.43
    jemah
    0.41
    bench
    0.41
    dad
    0.40
     v
    0.40
    嫁
    0.39
    Activations Density 0.048%

    No Known Activations