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. 8847
    Prev
    Next
    INDEX
    Explanations

    references to financial transactions and terms related to credit card usage

    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
    Reasonable
    -0.54
     sắp
    -0.49
    ábor
    -0.49
     praises
    -0.48
     Mait
    -0.48
     Diverse
    -0.48
     succinctly
    -0.47
    LOAT
    -0.47
     Reasonable
    -0.47
     diversified
    -0.47
    POSITIVE LOGITS
     counted
    1.38
     counts
    1.17
     automatically
    1.15
     count
    1.13
     counting
    1.10
    counted
    1.01
     ineligible
    1.00
    automatically
    0.96
     automáticamente
    0.93
     eligible
    0.93
    Activations Density 0.638%

    No Known Activations