© 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. 18-GEMMASCOPE-RES-16K
    11. 1875
    Prev
    Next
    INDEX
    Explanations

    sections of text that contain no activations, indicating it does not identify any relevant features

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

    following "All"

    np_acts-logits-general · gemini-2.0-flash

    Huntington disease and choroidal

    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
    #![
    -0.64
    ukone
    -0.52
    より
    -0.50
    structions
    -0.47
     الرخصة
    -0.46
    webElement
    -0.46
    webElementXpaths
    -0.45
     elettron
    -0.45
    $$
    -0.44
    ***
    -0.44
    POSITIVE LOGITS
     autorytatywna
    0.81
     passim
    0.75
    enumi
    0.73
     Signalez
    0.71
    NUMX
    0.70
     виправивши
    0.69
    >\<^
    0.68
    __':
    0.68
     дописавши
    0.67
    ServiceTest
    0.67
    Activations Density 0.031%

    No Known Activations