© 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. 14999
    Prev
    Next
    INDEX
    Explanations

    terms related to secrets, weapons, and technology

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

    preceding "are"

    np_acts-logits-general · gemini-2.0-flash

    all

    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
     spesso
    -0.68
     often
    -0.67
     quelquefois
    -0.64
     sometimes
    -0.63
     parfois
    -0.62
     tantôt
    -0.61
     misschien
    -0.61
    banyak
    -0.60
     algunos
    -0.59
     algunas
    -0.58
    POSITIVE LOGITS
     except
    1.33
    except
    1.18
     đều
    1.18
    Except
    1.14
     Except
    1.13
     excepto
    1.06
     sauf
    1.03
     kecuali
    1.02
     EXCEPT
    0.97
     including
    0.95
    Activations Density 0.429%

    No Known Activations