© 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. 4-GEMMASCOPE-RES-16K
    11. 2551
    Prev
    Next
    INDEX
    Explanations

    terms and phrases that describe mathematical functions and relationships

    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
     B
    -0.54
     rahat
    -0.45
     C
    -0.45
     a
    -0.43
     
    -0.42
     “
    -0.41
    žiu
    -0.41
     istimewa
    -0.40
     beszél
    -0.40
     an
    -0.40
    POSITIVE LOGITS
    IUrlHelper
    1.29
     beginnetje
    1.22
    contentLoaded
    1.10
    rungsseite
    1.09
    featureID
    1.08
    fjspx
    1.06
    GEBURTSDATUM
    1.04
     ModelExpression
    1.02
    InjectAttribute
    1.02
    WebVitals
    1.01
    Activations Density 0.679%

    No Known Activations