© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 21-GEMMASCOPE-RES-16K
    11. 14980
    Prev
    Next
    INDEX
    Explanations

    references to programming functions and methods related to object instantiation and management

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     TextAppearance
    -0.54
    Datuak
    -0.49
    rénées
    -0.45
    ixeira
    -0.45
     szóci
    -0.44
    gestone
    -0.43
    AnimationsModule
    -0.42
    eleste
    -0.41
    tegen
    -0.41
     DBNull
    -0.41
    POSITIVE LOGITS
     new
    4.26
    new
    3.59
     nuevos
    3.13
     nueva
    3.08
     nieuwe
    3.08
     nuevas
    3.05
     nuevo
    3.02
    新的
    3.00
     neuen
    2.88
     neue
    2.88
    Activations Density 1.890%

    No Known Activations