© 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 - 131k
    9. 20-GEMMASCOPE-RES-131K
    11. 12181
    Prev
    Next
    INDEX
    Explanations

    words related to suffering, conflict, and challenges

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

    widespread trouble or problems

    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
     مشين
    -0.73
    цездатний
    -0.73
    httphttps
    -0.63
    WireFormatLite
    -0.61
     فريبيس
    -0.59
     الحره
    -0.59
    rungsseite
    -0.58
    OGND
    -0.57
    AndEndTag
    -0.57
     InputDecoration
    -0.57
    POSITIVE LOGITS
     us
    0.63
     the
    0.52
     our
    0.48
    makeText
    0.47
     affecting
    0.41
     throughout
    0.40
     me
    0.39
    AssignableFrom
    0.39
    throughout
    0.39
     both
    0.39
    Activations Density 0.033%

    No Known Activations