© 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. 10-GEMMASCOPE-RES-16K
    11. 15026
    Prev
    Next
    INDEX
    Explanations

    references to accomplishments and notable achievements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    دانشنامهٔ
    -1.06
     nahilalakip
    -0.93
    MigrationBuilder
    -0.92
    webElementXpaths
    -0.92
    oa̍t
    -0.89
    Personendaten
    -0.88
    momix
    -0.79
     المعيارى
    -0.79
    GOTREF
    -0.78
    featureID
    -0.76
    POSITIVE LOGITS
     Serap
    0.37
     total
    0.36
     ‘
    0.35
    stat
    0.34
    raw
    0.34
     Viter
    0.34
    He
    0.34
    \
    0.33
    StringProperty
    0.32
     ran
    0.32
    Activations Density 2.540%

    No Known Activations