© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 21-GEMMASCOPE-RES-16K
    6. 7827
    Prev
    Next
    INDEX
    Explanations

    categories and answers in a structured format, akin to a quiz or data table

    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
    sen
    -0.48
    -------
    
    -0.47
    Super
    -0.44
    yto
    -0.44
    떻
    -0.44
    ParallelGroup
    -0.43
    lier
    -0.42
    super
    -0.42
    特别是
    -0.41
    Bett
    -0.40
    POSITIVE LOGITS
     nahilalakip
    0.81
    зулта
    0.74
     onCreateView
    0.74
    MemoryWarning
    0.73
     FetchType
    0.72
    VersionUID
    0.67
     JpaRepository
    0.65
    assertRaises
    0.64
    rawDesc
    0.63
    MockBean
    0.63
    Activations Density 0.501%

    No Known Activations