© 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. 22-GEMMASCOPE-RES-16K
    6. 8462
    Prev
    Next
    INDEX
    Explanations

    elements related to effective communication and interpersonal engagement

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

    following abstract concepts

    np_acts-logits-general · gemini-2.0-flash

    business, education, and social concepts

    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
    ⓘ
    -0.61
    uder
    -0.54
     rues
    -0.53
    ,:),
    -0.52
    ).[
    -0.52
    adh
    -0.51
    囗
    -0.51
    <caption>
    -0.50
    grees
    -0.49
    算了
    -0.48
    POSITIVE LOGITS
     always
    1.05
    always
    1.00
     siempre
    0.86
     plays
    0.85
     often
    0.84
     ALWAYS
    0.81
     needn
    0.80
     desempen
    0.78
     usually
    0.77
     jouent
    0.76
    Activations Density 0.659%

    No Known Activations