© 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. 307
    Prev
    Next
    INDEX
    Explanations

    mathematical notation and expressions related to statistical distributions and operations

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

    Mathematical expressions with parentheses and symbols

    np_acts-logits-general · gemini-2.0-flash

    `big` following closing brackets

    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
    ViewFeatures
    -0.77
    CppMethod
    -0.59
     mukana
    -0.52
    Geplaatst
    -0.51
    $.}
    -0.49
    /******/
    -0.48
    هو
    -0.47
     Rous
    -0.46
    المشاركات
    -0.46
     haline
    -0.45
    POSITIVE LOGITS
     ProtoMessage
    0.67
     الحره
    0.65
     himo
    0.62
    gwt
    0.59
    ukone
    0.53
    FactoryBean
    0.52
    right
    0.51
    
    0.51
    PasswordEncoder
    0.51
    Witam
    0.50
    Activations Density 1.084%

    No Known Activations