© 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. 20-GEMMASCOPE-RES-16K
    11. 8147
    Prev
    Next
    INDEX
    Explanations

    data structures and their properties

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

    UUIDs followed by specific characters

    np_acts-logits-general · gemini-2.0-flash

    hexadecimal identifiers

    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
    endphp
    -0.74
     tartalomajánló
    -0.69
     للمعارف
    -0.67
    脚注の使い方
    -0.60
    AddTagHelper
    -0.60
    TagMode
    -0.59
    antum
    -0.53
    IVEREF
    -0.53
    nyx
    -0.52
    _));
    -0.51
    POSITIVE LOGITS
     newOwner
    0.54
    TestBed
    0.53
    stateParams
    0.52
     Krum
    0.48
     dàng
    0.46
    conomie
    0.46
    polazione
    0.45
    elemField
    0.45
    ObjectName
    0.44
    Indented
    0.44
    Activations Density 0.098%

    No Known Activations