© 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-2-9B
    7. Residual Stream - 16k
    9. 2-GEMMASCOPE-RES-16K
    11. 7480
    Prev
    Next
    INDEX
    Explanations

    occurrences of the term "Nat" and related references throughout the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_2/width_16k/average_l0_67
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Dul
    -0.45
    EDEFAULT
    -0.44
    sbericht
    -0.43
    SharedDtor
    -0.41
     thuis
    -0.40
    kissen
    -0.39
     Compañía
    -0.38
     citoyens
    -0.38
    sendEmail
    -0.38
     outono
    -0.37
    POSITIVE LOGITS
     Nat
    0.84
    Nat
    0.82
     nat
    0.72
    :✨
    0.69
     NAT
    0.66
    NAT
    0.66
    nat
    0.64
    emp
    0.59
    loader
    0.57
     Norman
    0.55
    Activations Density 0.427%

    No Known Activations