© 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-2-9B-IT
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 121994
    Prev
    Next
    INDEX
    Explanations

    key terms and phrases related to health risks and medical conditions

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

    causes of death and disease

    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-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    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
    JsonHelper
    -0.46
    OrBuilder
    -0.40
    FieldBuilder
    -0.38
    FromNib
    -0.37
    Phones
    -0.36
     Pingback
    -0.35
    الحياه
    -0.34
     للمعارف
    -0.34
     besz
    -0.34
     Phones
    -0.34
    POSITIVE LOGITS
    gypti
    0.48
     causes
    0.47
     disaster
    0.45
    IonicModule
    0.45
    apimachinery
    0.45
     Alberta
    0.45
    の原因
    0.43
     cancer
    0.43
     対策
    0.42
     powietrza
    0.42
    Activations Density 0.049%

    No Known Activations