© 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. 20-GEMMASCOPE-RES-16K
    11. 6869
    Prev
    Next
    INDEX
    Explanations

    specific programming constructs or patterns

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Affirmations or confirmations

    np_acts-logits-general · gemini-2.0-flash

    affirmations and confirmations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     فريبيس
    -1.02
    endphp
    -0.88
     '\\;'
    -0.85
    etheless
    -0.84
    '])->
    -0.81
     שוליים
    -0.80
    >*/
    -0.79
    |}{$
    -0.78
     StatefulWidget
    -0.77
    WebServlet
    -0.77
    POSITIVE LOGITS
     inderdaad
    0.77
     @
    0.54
    そうですね
    0.53
    ↵↵
    0.53
    ..
    0.52
     indeed
    0.51
     exactly
    0.50
    !
    0.50
     tatsächlich
    0.49
    ครับ
    0.49
    Activations Density 0.553%

    No Known Activations