Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 5-GEMMASCOPE-RES-16K
    6. 1558
    Prev
    Next
    INDEX
    Explanations

    phrases that involve technical specifications or measurements related to electronic or engineering processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    createFrom
    -0.59
     näm
    -0.57
    alnız
    -0.55
     bará
    -0.55
     faktisk
    -0.55
    otesi
    -0.54
     européennes
    -0.54
    jekk
    -0.52
    Jereo
    -0.52
    styrelsen
    -0.51
    POSITIVE LOGITS
     sall
    0.54
    XmlType
    0.53
    ViewChild
    0.53
    #
    0.49
    yarnpkg
    0.49
    onAttach
    0.48
    forKey
    0.47
     Natalia
    0.47
    migrationBuilder
    0.46
     thyself
    0.46
    Activations Density 1.927%

    No Known Activations