Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 73487
    Prev
    Next
    INDEX
    Explanations

    phrases and terms associated with controversy and legal issues

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

    scandals, accusations, controversies, missed

    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
    efte
    -0.35
    깔
    -0.32
     refroid
    -0.30
     мы
    -0.30
     kami
    -0.30
    :✨
    -0.29
     presidencial
    -0.29
    我们是
    -0.29
    izoen
    -0.28
     pronon
    -0.28
    POSITIVE LOGITS
    SequentialGroup
    0.66
     scandals
    0.58
     accusations
    0.57
     controversies
    0.56
    ſammen
    0.53
    oneofs
    0.53
    Rptr
    0.52
    missed
    0.51
    GroupLayout
    0.50
    matitis
    0.49
    Activations Density 0.036%

    No Known Activations