© 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. 15468
    Prev
    Next
    INDEX
    Explanations

    references to the frequency of events occurring twice

    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
    o
    -0.59
    esl
    -0.59
    migrationBuilder
    -0.59
    তথ্যসূত্র
    -0.57
     single
    -0.56
    __":
    -0.56
    Kenneth
    -0.56
    pula
    -0.55
    वाल
    -0.54
     Kenneth
    -0.52
    POSITIVE LOGITS
     twice
    2.77
    twice
    2.69
     Twice
    2.50
    Twice
    2.49
     TWICE
    2.19
     thrice
    1.80
     zweimal
    1.80
    两次
    1.59
     mehrm
    1.29
     repeatedly
    1.17
    Activations Density 0.103%

    No Known Activations