© 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. 18-GEMMASCOPE-RES-16K
    11. 16169
    Prev
    Next
    INDEX
    Explanations

    keys and structure related to JSON data schemas

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

    Code snippets with brackets, colons, and quotation marks

    np_acts-logits-general · gemini-2.0-flash

    list entries

    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
     '',
    -0.58
    Искәрмәләр
    -0.55
    ConstraintMaker
    -0.52
     '';
    -0.51
    HtmlAttribute
    -0.47
     ''
    -0.46
     "";
    -0.45
    LinkId
    -0.45
     '':
    -0.45
     {},
    -0.44
    POSITIVE LOGITS
     listOf
    0.77
     list
    0.73
     []
    0.71
     List
    0.69
     [{
    0.69
    forChild
    0.68
    ListOf
    0.68
    NSArray
    0.66
     ujednoznacz
    0.65
    asList
    0.64
    Activations Density 0.122%

    No Known Activations