© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B-IT
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 1396
    Prev
    Next
    INDEX
    Explanations

    themes related to human existence, societal challenges, and the impact of historical events

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

    Follows a period

    np_acts-logits-general · gemini-2.0-flash

    societal challenges and states

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ſelben
    -0.69
    нгред
    -0.61
    endphp
    -0.61
    RegressionTest
    -0.60
     dieſem
    -0.60
     wiſſen
    -0.58
     otomatig
    -0.57
    MessageOf
    -0.57
     ſeinem
    -0.57
     للمعارف
    -0.57
    POSITIVE LOGITS
     下午
    0.31
     fometimes
    0.30
    波
    0.30
     sea
    0.30
     Zoo
    0.30
    face
    0.30
     Wave
    0.29
    part
    0.28
    奴
    0.27
    wave
    0.27
    Activations Density 0.321%

    No Known Activations