© 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. 22-GEMMASCOPE-RES-16K
    11. 10095
    Prev
    Next
    INDEX
    Explanations

    terms related to biochemical and pharmaceutical substances

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

    Chemical or pharmaceutical context

    np_acts-logits-general · gemini-2.0-flash

    drug and chemical names

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     "..\..\..\
    -0.89
     Paglinawan
    -0.85
     Италијани
    -0.85
     nakalista
    -0.83
    Vidite
    -0.82
    <bos>
    -0.79
     "..\..\
    -0.75
    ArrowToggle
    -0.68
     gainera
    -0.66
    InstrumentedTest
    -0.65
    POSITIVE LOGITS
     ModelExpression
    0.71
     BoxDecoration
    0.69
    AutoresizingMask
    0.66
     وتسجيلات
    0.65
     AdapterView
    0.57
    MethodImpl
    0.55
    ^(@)
    0.55
    ḫ
    0.54
    IFORNIA
    0.53
     تانيه
    0.53
    Activations Density 0.742%

    No Known Activations