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. 23-GEMMASCOPE-RES-16K
    6. 9029
    Prev
    Next
    INDEX
    Explanations

    terms and expressions related to online casinos and gambling promotions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 23-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_23/width_16k/average_l0_75
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.hook_resid_post
    Hook Layer
    23
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    gemeinden
    -0.57
    TagHelper
    -0.57
    CppMethod
    -0.55
    tagHelperRunner
    -0.55
    ילום
    -0.55
     Sears
    -0.55
    pperware
    -0.54
     CreateTagHelper
    -0.54
     cherchés
    -0.53
    ormal
    -0.53
    POSITIVE LOGITS
     casino
    0.96
     bonuses
    0.95
     bonus
    0.92
     deposit
    0.90
     Casino
    0.87
     depositing
    0.86
     Bonuses
    0.82
     Deposit
    0.82
    Casino
    0.81
    Bonuses
    0.80
    Activations Density 0.074%

    No Known Activations