© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 5-GEMMASCOPE-RES-16K
    11. 9385
    Prev
    Next
    INDEX
    Explanations

    phrases that indicate a majority or commonality among a group of entities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    zx
    -0.60
     pursuant
    -0.58
     liger
    -0.58
    افته
    -0.57
    auge
    -0.57
    不断的
    -0.56
    Nazi
    -0.55
    er
    -0.55
     dedo
    -0.55
     Spicer
    -0.54
    POSITIVE LOGITS
     fleste
    1.30
     flesta
    1.28
     meisten
    1.25
     meeste
    1.20
     plupart
    1.18
     most
    1.16
     большинство
    1.12
    most
    1.10
    Most
    1.04
     maioria
    0.99
    Activations Density 0.139%

    No Known Activations