© 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. 15144
    Prev
    Next
    INDEX
    Explanations

    terms related to formal processes and measurements

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

    ending in "ers", "ments", "signer", "mounts", or "tions"

    np_acts-logits-general · gemini-2.0-flash

    words ending in -ers or -ments

    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
    djangoproject
    -1.00
    المناصب
    -0.65
    +#+#
    -0.65
     Мексичка
    -0.63
    oneofs
    -0.58
     onOptions
    -0.57
    aleg
    -0.57
    awtextra
    -0.56
    imageshack
    -0.55
    bootstrapcdn
    -0.54
    POSITIVE LOGITS
     estekak
    0.74
    ings
    0.68
    仕方
    0.66
    able
    0.65
     Monfieur
    0.60
    ژاد
    0.55
    tempted
    0.55
     maestra
    0.52
    ódź
    0.51
     createSlice
    0.51
    Activations Density 1.119%

    No Known Activations