© 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. 12012
    Prev
    Next
    INDEX
    Explanations

    terms related to differentiation and classification in biological contexts

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

    Code or math differentiation

    np_acts-logits-general · gemini-2.0-flash

    differentiate, diversified, complicating

    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
    ness
    -0.96
    iness
    -0.87
    est
    -0.71
    CloseOperation
    -0.65
    ings
    -0.63
    fcntl
    -0.62
    meneu
    -0.59
     MotionEvent
    -0.59
    createStatement
    -0.58
     eventdata
    -0.58
    POSITIVE LOGITS
     hini
    0.80
    iation
    0.76
     myſelf
    0.74
    ATED
    0.72
    ../../../
    0.71
    ViewFeatures
    0.71
    ZED
    0.70
    ALLY
    0.69
    AutoresizingMask
    0.68
     autrement
    0.67
    Activations Density 0.717%

    No Known Activations