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. 8-GEMMASCOPE-RES-16K
    6. 4574
    Prev
    Next
    INDEX
    Explanations

    legal and regulatory citations and references, particularly those that pertain to guidelines and statutes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 8-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_8/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.hook_resid_post
    Hook Layer
    8
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ragen
    -0.58
    UnknownFields
    -0.54
    }{*}{
    -0.53
     leksikon
    -0.50
    மான
    -0.48
    <caption>
    -0.48
    談社
    -0.47
     quality
    -0.47
    GetEnumerator
    -0.47
     ModelExpression
    -0.47
    POSITIVE LOGITS
     lenker
    0.91
     Jefus
    0.67
     Monfieur
    0.66
     Baillargeon
    0.62
    abilia
    0.61
     Theſe
    0.60
    sonian
    0.60
     AsyncTask
    0.59
     themſelves
    0.59
     himſelf
    0.58
    Activations Density 1.280%

    No Known Activations