© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 16-GEMMASCOPE-RES-16K
    11. 13394
    Prev
    Next
    INDEX
    Explanations

    programming language syntax and structure related to class definitions and method declarations

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

    Code snippets and related symbols

    np_acts-logits-general · gemini-2.0-flash

    bridge and component names

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ComVisible
    -0.65
    ɵɵelementStart
    -0.61
    ције
    -0.56
    óa
    -0.55
    kháu
    -0.54
    AlterField
    -0.53
    URLException
    -0.53
     snippetHide
    -0.52
    IonicModule
    -0.52
    ஊ
    -0.52
    POSITIVE LOGITS
     piele
    0.51
    galan
    0.44
     fornito
    0.44
    靡
    0.43
     urmă
    0.43
     sposob
    0.43
    ]++;
    0.43
     unspecified
    0.42
     blah
    0.42
    yorsunuz
    0.42
    Activations Density 0.357%

    No Known Activations