© 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. 5487
    Prev
    Next
    INDEX
    Explanations

    elements related to programming and data processing

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

    Code-related abbreviations or variables

    np_acts-logits-general · gemini-2.0-flash

    variable initialization and assignment

    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
    <eos>
    -0.74
    ↵↵↵
    -0.50
    ()!=
    -0.50
    MediaStore
    -0.49
    ()==
    -0.48
    amodel
    -0.47
    営
    -0.47
    vele
    -0.46
    ]=="
    -0.45
     ندارد
    -0.45
    POSITIVE LOGITS
    StoryboardSegue
    0.87
    ConstraintMaker
    0.84
     AssemblyCulture
    0.80
    XmlEnum
    0.78
     الرياضيه
    0.77
    DotNetBar
    0.76
     resourceCulture
    0.74
    extAlignment
    0.72
     ―――――
    0.71
     Telex
    0.68
    Activations Density 0.090%

    No Known Activations