© 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. 25-GEMMASCOPE-RES-16K
    11. 11788
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions and operations related to linear algebra, specifically vector spaces and transformations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.hook_resid_post
    Hook Layer
    25
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    IsContent
    -0.71
    ftagPool
    -0.58
    __*/
    -0.55
    makeConstraints
    -0.55
     Haig
    -0.52
    tagext
    -0.52
    ReusableCell
    -0.52
     Estadual
    -0.52
    مصادر
    -0.51
     Widodo
    -0.51
    POSITIVE LOGITS
     vector
    1.50
     vectors
    1.42
     Vector
    1.37
     Vectors
    1.25
    Vector
    1.23
    vector
    1.19
     vektor
    1.16
    vectors
    1.13
     벡터
    1.11
     VECTOR
    1.11
    Activations Density 1.470%

    No Known Activations