© 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. 14-GEMMASCOPE-RES-16K
    11. 3410
    Prev
    Next
    INDEX
    Explanations

    elements of code dealing with comments and function execution

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 14-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_14/width_16k/average_l0_84
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.14.hook_resid_post
    Hook Layer
    14
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    DockStyle
    -1.27
     Roskov
    -1.18
    DeleteBehavior
    -1.02
     виправивши
    -1.01
     ſtate
    -1.00
     fevere
    -1.00
     ſever
    -0.99
    ViewFeatures
    -0.98
     purpoſe
    -0.98
     ſeveral
    -0.96
    POSITIVE LOGITS
     //
    0.58
     (
    0.54
     for
    0.51
    ↵
    0.50
     
    0.49
     and
    0.48
    Alright
    0.47
     javafx
    0.47
     Additionally
    0.46
     A
    0.45
    Activations Density 0.170%

    No Known Activations