© 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 EvalsExportsinterp-engineNEWAPI 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. 8537
    Prev
    Next
    INDEX
    Explanations

    names of people and specific entities related to various contexts

    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
    Kuz
    -1.09
     RZ
    -1.07
     Lizzy
    -1.06
     Kuz
    -1.05
     Caz
    -1.03
    zzz
    -1.01
    rz
    -1.01
     EZ
    -1.00
    zone
    -0.97
    z
    -0.97
    POSITIVE LOGITS
     păr
    0.78
    olingo
    0.70
     ló
    0.69
    viedo
    0.68
    baidu
    0.67
    ospel
    0.67
     singur
    0.66
     Sér
    0.65
    первых
    0.65
     dumne
    0.64
    Activations Density 1.991%

    No Known Activations