© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 25-GEMMASCOPE-RES-16K
    6. 2484
    Prev
    Next
    INDEX
    Explanations

    shared references to sporting organizations and events, particularly within the context of basketball leagues

    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
    ModelAdmin
    -0.55
     rospy
    -0.53
    TypedDataSet
    -0.53
    MessageTagHelper
    -0.52
     endblock
    -0.50
     Absor
    -0.49
     ligiloj
    -0.49
     <>",
    -0.48
    FieldError
    -0.48
    IPAC
    -0.48
    POSITIVE LOGITS
     NRL
    0.69
    KommentareTeilen
    0.64
     Origin
    0.63
    NRL
    0.61
     Broncos
    0.61
     Cowboys
    0.59
     halves
    0.56
     dummy
    0.56
     chi̍t
    0.56
     betweenstory
    0.56
    Activations Density 0.179%

    No Known Activations