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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & 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. 16-GEMMASCOPE-RES-16K
    6. 6261
    Prev
    Next
    INDEX
    Explanations

    references to financial instruments and international locations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/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.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
    клопе
    -0.93
     CreateTagHelper
    -0.76
    tanleria
    -0.73
     disambiguazione
    -0.71
     Dhaka
    -0.69
    ніципалі
    -0.68
    gameserver
    -0.68
     Phnom
    -0.68
    下载附件
    -0.67
     bangkok
    -0.66
    POSITIVE LOGITS
     South
    0.63
    IMPORTED
    0.56
     Norte
    0.52
     West
    0.52
    ppelin
    0.52
     East
    0.49
     North
    0.49
     muualla
    0.48
     emerging
    0.47
    Errorf
    0.47
    Activations Density 0.190%

    No Known Activations