© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 131k
    9. 20-GEMMASCOPE-RES-131K
    11. 104317
    Prev
    Next
    INDEX
    Explanations

    phrases related to legal justification and political rhetoric

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_131k/average_l0_114
    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
    Prote
    -0.35
    setLayoutManager
    -0.35
     proteger
    -0.33
     protecting
    -0.33
     protect
    -0.32
     prote
    -0.32
    prote
    -0.32
     protects
    -0.30
     okru
    -0.30
     Prote
    -0.28
    POSITIVE LOGITS
    MockMvc
    0.70
     ExecuteAsync
    0.66
     noDo
    0.63
    #+#
    0.62
    RenderAtEndOf
    0.60
    istoitu
    0.58
    (!__
    0.57
    BufferException
    0.57
    IsMutable
    0.56
     taunt
    0.56
    Activations Density 0.082%

    No Known Activations