© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 3-GEMMASCOPE-RES-16K
    6. 12564
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "when."

    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
     bezeichneter
    -1.05
    ArrowToggle
    -0.85
     Fid
    -0.78
    افظة
    -0.70
     SEDS
    -0.69
    IsNull
    -0.68
    miary
    -0.68
    というわけで
    -0.67
     EXIT
    -0.66
     Livermore
    -0.65
    POSITIVE LOGITS
     when
    2.62
    when
    2.37
     WHEN
    2.15
     When
    2.03
    When
    2.02
     cuando
    1.99
    WHEN
    1.95
     quando
    1.87
    cuando
    1.77
     när
    1.70
    Activations Density 0.104%

    No Known Activations