© 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 EvalsExportsinterp-engineNEWAPI 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. 6320
    Prev
    Next
    INDEX
    Explanations

    questions related to timing or conditional situations

    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
     bezeichneter
    -0.85
    ArrowToggle
    -0.83
     Fid
    -0.78
    افظة
    -0.70
     частности
    -0.68
    čko
    -0.64
     Livermore
    -0.64
    曖昧さ回避
    -0.64
    Hush
    -0.61
    ษ
    -0.61
    POSITIVE LOGITS
     when
    2.06
    when
    1.92
     WHEN
    1.80
    WHEN
    1.68
    When
    1.66
     When
    1.65
     cuando
    1.62
    cuando
    1.54
     quando
    1.49
     när
    1.48
    Activations Density 0.103%

    No Known Activations