© 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. 18-GEMMASCOPE-RES-16K
    11. 6742
    Prev
    Next
    INDEX
    Explanations

    elements and functions related to AngularJS directives and their implementations

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

    AngularJS code or directives

    np_acts-logits-general · gemini-2.0-flash

    AngularJS directives and controllers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     sake
    -0.96
    RegressionTest
    -0.74
     Sake
    -0.70
    ake
    -0.64
     jScrollPane
    -0.60
    findpost
    -0.57
    ゴリー
    -0.57
    atemala
    -0.56
    Atsauces
    -0.55
     Fuchs
    -0.53
    POSITIVE LOGITS
    ngdoc
    0.67
     angular
    0.53
     ng
    0.52
    ArrowToggle
    0.49
     Angular
    0.49
     (€
    0.49
    scope
    0.49
    ImageContext
    0.48
    vm
    0.48
    Ctrl
    0.48
    Activations Density 0.209%

    No Known Activations