Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 11-GEMMASCOPE-RES-16K
    6. 6984
    Prev
    Next
    INDEX
    Explanations

    terms related to judicial discretion and its abuse

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Hook Layer
    11
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    orteur
    -0.84
     useCallback
    -0.81
     للمعارف
    -0.79
     Vard
    -0.79
     uhd
    -0.79
    Steph
    -0.79
    Rah
    -0.79
    mainPanel
    -0.79
     referência
    -0.78
    Thierry
    -0.77
    POSITIVE LOGITS
     Mühle
    0.69
    Synd
    0.65
     Abra
    0.65
    setDuration
    0.61
     SafeMath
    0.61
     unangemessene
    0.61
    acks
    0.58
     Gar
    0.58
    tease
    0.58
     blockade
    0.57
    Activations Density 0.678%

    No Known Activations