© 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. 3800
    Prev
    Next
    INDEX
    Explanations

    references to languages or terms related to linguistic studies

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

    following "that", "the", "a", "its", or "same"

    np_acts-logits-general · gemini-2.0-flash

    word or proper noun name

    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
    orsese
    -0.54
    OrBuilder
    -0.52
     kaarangay
    -0.43
    }))
    -0.43
    retario
    -0.41
    }));
    -0.40
    FilterChain
    -0.40
    withOpacity
    -0.39
     Arhivirano
    -0.38
    KURZBESCHREIBUNG
    -0.37
    POSITIVE LOGITS
     name
    3.25
     names
    2.82
    name
    2.63
     Name
    2.52
     NAME
    2.48
    Name
    2.33
     Names
    2.28
     Namen
    2.22
    NAME
    2.21
     naam
    2.15
    Activations Density 0.871%

    No Known Activations