© 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. 16243
    Prev
    Next
    INDEX
    Explanations

    elements and attributes related to data storage and system configuration

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

    Properties related to size, width, or capacity

    np_acts-logits-general · gemini-2.0-flash

    parameters and measurements

    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
    hasErrors
    -0.50
     Di
    -0.49
     keberadaan
    -0.47
     autorytatywna
    -0.47
     Vol
    -0.45
    énario
    -0.44
     utafitiHapana
    -0.44
     v
    -0.42
     المعيارى
    -0.42
     координа
    -0.41
    POSITIVE LOGITS
    WriteTagHelper
    0.82
     themſelves
    0.80
     maximum
    0.79
     myſelf
    0.78
    arParams
    0.76
    WebVitals
    0.75
     faſt
    0.75
     tolerance
    0.75
     leſs
    0.75
     himſelf
    0.74
    Activations Density 0.408%

    No Known Activations