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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 16-GEMMASCOPE-RES-16K
    6. 1818
    Prev
    Next
    INDEX
    Explanations

    expressions related to government, policies, and examples of success in governance

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

    after "that" and "of"

    np_acts-logits-general · gemini-2.0-flash

    power of

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ensure
    -0.47
    التالي
    -0.46
    UrlResolution
    -0.46
    renda
    -0.45
    Guarantee
    -0.45
    bucht
    -0.44
     news
    -0.44
    medes
    -0.44
    έ
    -0.44
    踞
    -0.43
    POSITIVE LOGITS
    原來
    0.69
    HtmlAttribute
    0.68
    原来
    0.60
    HasAnnotation
    0.57
     can
    0.56
    RunAsync
    0.56
    ípios
    0.56
    تقاوى
    0.56
     Syrie
    0.55
    Vidite
    0.55
    Activations Density 0.260%

    No Known Activations