© 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. 2-GEMMASCOPE-RES-16K
    11. 16299
    Prev
    Next
    INDEX
    Explanations

    contexts emphasizing a pattern of regularity or consistency

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Balfour
    -0.76
     uParam
    -0.71
     Biosciences
    -0.67
    thschild
    -0.67
    ANSA
    -0.66
    tesla
    -0.64
     attribution
    -0.62
    RTLR
    -0.62
     Nielsen
    -0.61
     BNE
    -0.60
    POSITIVE LOGITS
     regular
    3.65
    regular
    3.39
     Regular
    3.32
    Regular
    3.30
     REGULAR
    3.05
    REGULAR
    2.91
     regulares
    2.63
     regulars
    2.36
     régulier
    2.33
     regularly
    2.28
    Activations Density 0.090%

    No Known Activations