© 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. 3-GEMMASCOPE-RES-16K
    6. 6701
    Prev
    Next
    INDEX
    Explanations

    references to judicial districts or courts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_3/width_16k/average_l0_90
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    taminophen
    -0.53
    OGND
    -0.42
    ilever
    -0.41
    pylene
    -0.41
     semula
    -0.40
    SneakyThrows
    -0.39
    tifkan
    -0.39
    usehen
    -0.37
    原始内容存档
    -0.37
     Ouvrez
    -0.36
    POSITIVE LOGITS
     District
    4.06
     district
    4.00
    District
    3.80
    district
    3.52
     DISTRICT
    3.52
    DISTRICT
    3.09
     districts
    3.09
     Districts
    3.05
    districts
    2.69
     distrito
    2.52
    Activations Density 0.113%

    No Known Activations