Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 65k
    5. 16-GEMMASCOPE-RES-65K
    6. 53008
    Prev
    Next
    INDEX
    Explanations

    instances of reported human cases related to a specific virus

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

    cases of

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_65k/average_l0_128
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     aidant
    -0.48
     popular
    -0.47
    top
    -0.42
     espl
    -0.42
    hen
    -0.42
     meg
    -0.41
     implements
    -0.41
     rend
    -0.41
     selected
    -0.40
    Selected
    -0.40
    POSITIVE LOGITS
     Jefus
    1.04
    Tikang
    0.99
     Efq
    0.96
     houſe
    0.92
     itſelf
    0.91
     myſelf
    0.90
     Anſ
    0.88
     Diſ
    0.86
     ſtate
    0.85
     fubject
    0.85
    Activations Density 0.048%

    No Known Activations