© 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. 5-GEMMASCOPE-RES-16K
    11. 8938
    Prev
    Next
    INDEX
    Explanations

    concepts related to theoretical frameworks and principles

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Utilizamos
    -0.53
     ویکی‌پدیای
    -0.51
     resté
    -0.51
     berätt
    -0.50
     belegt
    -0.49
    TAINMENT
    -0.48
    prechpartner
    -0.48
    ferent
    -0.47
     vectorielle
    -0.47
     sutil
    -0.47
    POSITIVE LOGITS
     theoretically
    0.97
     Technically
    0.94
    Technically
    0.93
     technically
    0.92
     Theore
    0.89
     nominally
    0.86
    Theore
    0.84
    sätzlich
    0.80
    nically
    0.79
    Ideally
    0.76
    Activations Density 0.339%

    No Known Activations