© 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. 12-GEMMASCOPE-RES-16K
    11. 8321
    Prev
    Next
    INDEX
    Explanations

    technical or mathematical terms associated with data analysis and algorithmic processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     MainAxisSize
    -0.69
    WebElementEntity
    -0.68
     "..\..\..\
    -0.65
     "..\..\
    -0.59
     Wikiseite
    -0.59
    Pranala
    -0.59
    blica
    -0.57
     intermédiaire
    -0.57
     مرئيه
    -0.57
     EconPapers
    -0.56
    POSITIVE LOGITS
    msgTypes
    0.51
    iprot
    0.50
    +#+#
    0.48
     nào
    0.48
    forName
    0.47
    nextProps
    0.46
     chosen
    0.46
     ModelExpression
    0.45
    ỡng
    0.43
     Chosen
    0.43
    Activations Density 2.002%

    No Known Activations