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. 15-GEMMASCOPE-RES-16K
    6. 4999
    Prev
    Next
    INDEX
    Explanations

    events related to political scandals and legal issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_15/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    her
    -0.50
     Vol
    -0.50
     Her
    -0.49
    ilen
    -0.49
    DataContract
    -0.48
    Хьажоргаш
    -0.47
    Explanation
    -0.44
    CDCl
    -0.44
    Vol
    -0.43
     Krank
    -0.43
    POSITIVE LOGITS
     виправивши
    0.95
     Theſe
    0.90
    TagMode
    0.87
    expandindo
    0.85
     >=",
    0.81
     itſelf
    0.81
    hdashline
    0.80
     متعلقه
    0.77
     Efq
    0.75
    ^(@)
    0.74
    Activations Density 0.662%

    No Known Activations