© 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
    7. Residual Stream - 16k
    9. 21-GEMMASCOPE-RES-16K
    11. 2627
    Prev
    Next
    INDEX
    Explanations

    terms related to legal and judicial processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_21/width_16k/average_l0_129
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     olvido
    -0.52
     asegurado
    -0.41
     férias
    -0.38
     ricordare
    -0.37
     Erzb
    -0.37
     democrática
    -0.37
     dần
    -0.37
     konge
    -0.37
     sicura
    -0.36
     esclavos
    -0.36
    POSITIVE LOGITS
     prevent
    0.90
    prevent
    0.83
     Prevent
    0.82
     prevented
    0.82
     Preventing
    0.79
     preven
    0.79
     preventing
    0.78
     Preven
    0.77
     PREVENT
    0.77
     prevention
    0.75
    Activations Density 0.527%

    No Known Activations