© 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. 22-GEMMASCOPE-RES-16K
    6. 5884
    Prev
    Next
    INDEX
    Explanations

    financial and regulatory terms related to gambling and the management of funds

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_22/width_16k/average_l0_123
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    COVID
    -0.90
     incentiv
    -0.90
     COVID
    -0.87
     microbiome
    -0.87
     impactful
    -0.87
    https
    -0.86
     onboarding
    -0.85
    Covid
    -0.79
    ​​​​​​​
    -0.78
     LGBTQ
    -0.78
    POSITIVE LOGITS
     muß
    0.65
     idéia
    0.54
    faßt
    0.53
     daß
    0.50
    RegressionTest
    0.49
     ``
    0.47
     mußten
    0.47
     mußte
    0.46
    BeginContext
    0.43
     läßt
    0.41
    Activations Density 1.448%

    No Known Activations