© 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-2-2B
    7. Residual Stream - 16k
    9. 25-GEMMASCOPE-RES-16K
    11. 1154
    Prev
    Next
    INDEX
    Explanations

    mentions of judicial and legal terminology related to counties and townships

    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
    tically
    -0.59
    MLLoader
    -0.57
     الدولى
    -0.56
    venido
    -0.56
    bootstrapcdn
    -0.56
     kì
    -0.55
     الوطنيه
    -0.55
     باسم
    -0.54
    äiv
    -0.50
    kloped
    -0.49
    POSITIVE LOGITS
     counties
    0.65
     Mult
    0.60
     Dane
    0.57
     Polk
    0.56
    olusi
    0.56
     Contra
    0.56
     Weld
    0.56
     Putnam
    0.55
     Greene
    0.55
    Mult
    0.54
    Activations Density 0.459%

    No Known Activations