© 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-2-9B
    4. Residual Stream - 16k
    5. 12-GEMMASCOPE-RES-16K
    6. 10922
    Prev
    Next
    INDEX
    Explanations

    references to encoding formats and protocols

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 12-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_12/width_16k/average_l0_130
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     izquierdo
    -0.57
    Cuál
    -0.57
     trụ
    -0.55
    acamata
    -0.54
    */].
    -0.54
     Strahl
    -0.53
    cuál
    -0.52
     Schicks
    -0.52
    actéristi
    -0.51
     Komunikasi
    -0.51
    POSITIVE LOGITS
     en
    1.15
     En
    1.09
    En
    0.99
     EN
    0.98
    en
    0.78
    EN
    0.67
     enclave
    0.66
     Ennis
    0.64
     Ena
    0.64
     unen
    0.60
    Activations Density 0.100%

    No Known Activations