© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 65k
    5. 16-GEMMASCOPE-RES-65K
    6. 30646
    Prev
    Next
    INDEX
    Explanations

    instances of labeled figures or sections within a document

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

    numbers, code, and doubt clarification

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_65k/average_l0_128
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     informée
    -0.47
    FromServer
    -0.45
     model
    -0.43
    BY
    -0.42
     mod
    -0.41
     '
    -0.41
     either
    -0.40
    by
    -0.40
    NSYLVANIA
    -0.40
    ili
    -0.40
    POSITIVE LOGITS
    tagHelper
    1.18
    ')):
    1.02
    TagHelper
    1.02
    "):
    
    1.01
    '):
    
    0.98
    '))
    
    0.93
    TagHelpers
    0.93
    TagMode
    0.92
    BeginContext
    0.87
    DockStyle
    0.87
    Activations Density 0.000%

    No Known Activations