© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 3-GEMMASCOPE-RES-16K
    11. 1258
    Prev
    Next
    INDEX
    Explanations

    instances of dates and specific numerical data in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ͜ʖ
    -0.65
    Personendaten
    -0.53
    ÕES
    -0.53
    mingbird
    -0.52
    iros
    -0.51
     knuckles
    -0.51
    bildung
    -0.51
    toor
    -0.51
     Hartmann
    -0.50
    permum
    -0.50
    POSITIVE LOGITS
    OrBuilder
    0.72
    DoubleQuotes
    0.70
    verwijspagina
    0.65
    ).—
    0.60
     actionMode
    0.59
    ApiModelProperty
    0.56
    ,‎
    0.55
    IsMutable
    0.55
     SafeMath
    0.53
    phosa
    0.53
    Activations Density 0.129%

    No Known Activations