© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 15927
    Prev
    Next
    INDEX
    Explanations

    specific numerical values or statistics

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

    appearing before "I", "The", or "Q"

    np_acts-logits-general · gemini-2.0-flash

    The Departed

    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
     verdaderos
    -0.45
    <b>
    -0.43
    <eos>
    -0.42
    ↵↵
    -0.40
     issued
    -0.40
    <sup>
    -0.39
     verdadero
    -0.37
    まで
    -0.37
     öz
    -0.36
    }
    -0.36
    POSITIVE LOGITS
     resourceCulture
    1.23
    webElementXpaths
    1.21
     '\\;'
    1.14
    yntaxException
    1.06
     snippetHide
    1.05
    findpost
    1.05
    InjectAttribute
    1.03
    MigrationBuilder
    1.03
     الحره
    1.01
     ProtoMessage
    1.00
    Activations Density 0.048%

    No Known Activations