© 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 - 65k
    5. 16-GEMMASCOPE-RES-65K
    6. 27780
    Prev
    Next
    INDEX
    Explanations

    references to legal cases and statutes

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

    legal citations year ends with 9

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_65k/average_l0_128
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ſche
    -1.13
    Sucesor
    -1.08
    AndEndTag
    -1.05
    ConstraintMaker
    -1.05
    PerformLayout
    -1.05
     ſtate
    -1.05
    )");
    
    -1.03
    tagHelperRunner
    -1.02
     houſe
    -1.02
    原始内容存档于
    -1.01
    POSITIVE LOGITS
     A
    0.60
    ic
    0.50
     assoluto
    0.50
     a
    0.50
     Pink
    0.49
     I
    0.49
     Mil
    0.49
     Mal
    0.48
     (
    0.48
     \
    0.48
    Activations Density 0.059%

    No Known Activations