© 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. 3-GEMMASCOPE-RES-16K
    6. 10598
    Prev
    Next
    INDEX
    Explanations

    symbols and formatting used in mathematical and scientific notation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    __':
    
    -0.48
    IAm
    -0.47
    odils
    -0.47
    Revenir
    -0.46
    χρι
    -0.45
     betweenstory
    -0.44
    ísi
    -0.43
    uestamente
    -0.43
     SLIP
    -0.42
    োগ
    -0.42
    POSITIVE LOGITS
    FieldBuilder
    0.93
    OGND
    0.89
    EndInit
    0.87
    encodeWith
    0.86
    forRoot
    0.83
     purpoſe
    0.76
    InputBorder
    0.76
     EnglishChoose
    0.74
    forChild
    0.74
     ſtate
    0.73
    Activations Density 0.153%

    No Known Activations