© 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. 4-GEMMASCOPE-RES-16K
    11. 342
    Prev
    Next
    INDEX
    Explanations

    mathematical notation related to matrices and their transpositions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.hook_resid_post
    Hook Layer
    4
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Демографія
    -0.53
     regla
    -0.52
    QMetaType
    -0.51
    geschenk
    -0.49
     arit
    -0.48
    ardless
    -0.48
    busch
    -0.47
     AssemblyTitle
    -0.47
    IsContent
    -0.47
    허
    -0.47
    POSITIVE LOGITS
     Etr
    0.59
    arrings
    0.57
    transpose
    0.56
    ]';
    0.56
    %");
    0.56
    SYM
    0.55
    GIVEREF
    0.52
    
    0.52
    BoxLayout
    0.51
     FontFamily
    0.50
    Activations Density 0.853%

    No Known Activations