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. 24-GEMMASCOPE-RES-16K
    6. 14870
    Prev
    Next
    INDEX
    Explanations

    content related to healthcare policies and practices

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Followed by a verb

    np_acts-logits-general · gemini-2.0-flash

    tax problems

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     epo
    -0.25
     dou
    -0.25
     loch
    -0.24
     sund
    -0.24
     ferr
    -0.23
     deli
    -0.23
     imam
    -0.23
     grom
    -0.23
     garda
    -0.23
     brun
    -0.23
    POSITIVE LOGITS
     découver
    0.50
     vectoriales
    0.49
     dépens
    0.49
     fermés
    0.47
     étan
    0.47
     cérami
    0.47
     démocr
    0.47
     Dog
    0.47
     Scal
    0.47
     peindre
    0.47
    Activations Density 30.130%

    No Known Activations