© 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. 112389
    Prev
    Next
    INDEX
    Explanations

    phrases related to digital communication and awareness of online privacy

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

    spread out, lot of

    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
     enfans
    -0.40
     marins
    -0.37
     state
    -0.33
     itemprop
    -0.33
     concerned
    -0.32
     shared
    -0.31
     Merah
    -0.30
     internally
    -0.29
     ſtate
    -0.29
     communs
    -0.29
    POSITIVE LOGITS
     Numerade
    0.88
     EClass
    0.80
    dafx
    0.78
     Lightboxes
    0.73
     виправивши
    0.73
    SharedCtor
    0.73
     resourceCulture
    0.72
     незавершена
    0.71
     Italijanski
    0.68
    verifyException
    0.68
    Activations Density 0.008%

    No Known Activations