© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 4553
    Prev
    Next
    INDEX
    Explanations

    phrases indicative of product advice and financial disclosures

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

    Preceding tokens of the word "example"

    np_acts-logits-general · gemini-2.0-flash

    exampleexamples

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    }))
    -0.67
    rouvez
    -0.61
     onBackPressed
    -0.60
    }],
    -0.59
    SEGUIR
    -0.58
    __]
    -0.56
    PagerAdapter
    -0.55
    StoryboardSegue
    -0.55
     AppBar
    -0.54
    المناصب
    -0.54
    POSITIVE LOGITS
     example
    2.92
     examples
    2.92
     Example
    2.57
    Example
    2.53
    example
    2.50
     Examples
    2.49
    examples
    2.47
    Examples
    2.40
     EXAMPLE
    2.35
     exemples
    2.34
    Activations Density 1.100%

    No Known Activations