© 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. 22-GEMMASCOPE-RES-16K
    6. 11201
    Prev
    Next
    INDEX
    Explanations

    concepts related to social and healthcare systems, particularly focusing on issues of inequity and the impacts of policies

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

    preceding problems or challenges

    np_acts-logits-general · gemini-2.0-flash

    major difficulties or limitations

    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
    Tikang
    -0.70
    Tembelea
    -0.64
    rungsseite
    -0.64
    MigrationBuilder
    -0.60
    참고
    -0.60
    setViewName
    -0.59
    مصادر
    -0.58
    ագրություններ
    -0.57
    Espèce
    -0.56
    GenerationType
    -0.55
    POSITIVE LOGITS
     hurdles
    1.01
     pitfalls
    0.96
     obstacles
    0.96
     barriers
    0.89
     stumbling
    0.85
     hurdle
    0.80
     parado
    0.80
     thorny
    0.78
     challenges
    0.78
     gaping
    0.78
    Activations Density 0.663%

    No Known Activations