© 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 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. 15508
    Prev
    Next
    INDEX
    Explanations

    numeric values and references to participant/sample demographics in research studies

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

    (n= followed by a number

    np_acts-logits-general · gemini-2.0-flash

    sample size notations (n = X)

    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
    "।
    -0.44
     ""
    -0.43
    ：
    -0.43
     màng
    -0.40
    sillo
    -0.40
    "".
    -0.39
     policies
    -0.39
    ・・・」
    -0.39
    []){
    -0.39
    ?!”
    -0.38
    POSITIVE LOGITS
     n
    1.09
    n
    0.91
    تقاوى
    0.80
    PageRoute
    0.73
    RenderAtEndOf
    0.73
    GraphicsUnit
    0.69
    verwijspagina
    0.68
    IntoConstraints
    0.67
    LLocation
    0.66
     CreateTagHelper
    0.65
    Activations Density 0.584%

    No Known Activations