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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 3-GEMMASCOPE-RES-16K
    11. 12683
    Prev
    Next
    INDEX
    Explanations

    references to software components and assemblies in a technical context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    tagHelperRunner
    -1.09
    enumi
    -0.99
    NameInMap
    -0.91
    abestanden
    -0.90
     consultato
    -0.87
    DoubleQuotes
    -0.87
     unknownFields
    -0.86
     nahilalakip
    -0.86
     ویکی‌پدیا
    -0.86
    djangoproject
    -0.83
    POSITIVE LOGITS
     possible
    0.44
    tahui
    0.44
    /}
    0.42
    datagrid
    0.42
     utiles
    0.42
    穫
    0.42
     sécurité
    0.41
    _=
    0.41
    ">{{$
    0.40
     novel
    0.40
    Activations Density 0.101%

    No Known Activations