© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 7123
    Prev
    Next
    INDEX
    Explanations

    terms related to methods and tools used in scientific research

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

    "[Something] was/is/are used"

    np_acts-logits-general · gemini-2.0-flash

    was used widely

    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
    QMetaType
    -0.60
     propOrder
    -0.58
    AlterField
    -0.56
    ########.
    -0.56
     ProtoMessage
    -0.56
     autorytatywna
    -0.55
     jadx
    -0.55
    bilisi
    -0.54
    ۣ
    -0.53
    Datuak
    -0.53
    POSITIVE LOGITS
     use
    2.90
     Use
    2.42
     usage
    2.42
    Use
    2.37
    use
    2.35
     used
    2.34
     uses
    2.21
     gebruik
    2.14
    used
    2.10
     USE
    2.07
    Activations Density 1.378%

    No Known Activations