© 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. 2-GEMMASCOPE-RES-16K
    11. 1937
    Prev
    Next
    INDEX
    Explanations

    references to examples and instances

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Kirsch
    -0.54
    ontin
    -0.52
    ähte
    -0.51
     Wau
    -0.51
    riek
    -0.50
    werve
    -0.50
     Chet
    -0.49
    ']/
    -0.49
     thinly
    -0.48
    ueves
    -0.48
    POSITIVE LOGITS
     например
    1.26
     bijvoorbeeld
    1.26
    Например
    1.25
     Например
    1.17
    например
    1.17
     Misalnya
    1.17
     esempio
    1.15
    tamment
    1.14
     exemple
    1.13
     eksempel
    1.13
    Activations Density 0.497%

    No Known Activations