© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 2-GEMMASCOPE-RES-16K
    6. 8701
    Prev
    Next
    INDEX
    Explanations

    references to pots and related variations in context

    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
     referrerpolicy
    -0.51
     Vital
    -0.49
     Prima
    -0.48
    LEncoder
    -0.47
    CompilerServices
    -0.46
     Marketing
    -0.46
    allos
    -0.45
    newpage
    -0.45
    fiche
    -0.44
     Universal
    -0.44
    POSITIVE LOGITS
     pot
    3.22
    Pot
    2.50
     Pot
    2.45
    pot
    2.38
     pots
    2.13
     POT
    1.95
     Pots
    1.78
    POT
    1.78
    pots
    1.73
     Topf
    1.38
    Activations Density 0.113%

    No Known Activations