© 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-2-2B
    4. Residual Stream - 16k
    5. 25-GEMMASCOPE-RES-16K
    6. 12182
    Prev
    Next
    INDEX
    Explanations

    statements related to legal processes and court proceedings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.hook_resid_post
    Hook Layer
    25
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     stället
    -1.09
     verksamhet
    -1.02
     varandra
    -0.98
     chré
    -0.98
     élas
    -0.97
     démocr
    -0.97
     vägen
    -0.97
     igång
    -0.96
     chrétiens
    -0.96
     colorés
    -0.95
    POSITIVE LOGITS
    HomeAsUpEnabled
    0.61
    Pozdrawiam
    0.52
     ol
    0.48
    A
    0.47
    S
    0.47
    Seguir
    0.46
    Dazu
    0.46
    I
    0.46
     Leche
    0.45
    Underline
    0.44
    Activations Density 0.915%

    No Known Activations