© 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. 20-GEMMASCOPE-RES-16K
    11. 285
    Prev
    Next
    INDEX
    Explanations

    numerical values and mathematical operations

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

    Negative correlations/associations

    np_acts-logits-general · gemini-2.0-flash

    negative numbers and correlations

    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
    kol
    -0.41
    bru
    -0.40
    〝
    -0.38
    <<<<<<<<<<<<
    -0.38
    Skocz
    -0.37
    koń
    -0.36
     sett
    -0.36
    mazoo
    -0.36
    ulosa
    -0.36
    apr
    -0.36
    POSITIVE LOGITS
     negative
    2.47
     Negative
    2.29
    Negative
    2.19
    negative
    2.18
     NEGATIVE
    2.08
     (-
    2.08
     positive
    1.88
     $(-
    1.87
    NEGATIVE
    1.83
     négatif
    1.83
    Activations Density 3.967%

    No Known Activations