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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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 - 16k
    5. 9-GEMMASCOPE-RES-16K
    6. 15662
    Prev
    Next
    INDEX
    Explanations

    words conveying continuity or persistence

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_9/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.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ]();
    -0.88
    oa̍t
    -0.86
    aiuto
    -0.80
    ="{
    -0.77
    entile
    -0.76
    ftagPool
    -0.76
     "..\..\..\
    -0.74
    lucky
    -0.73
    
    -0.73
    effetto
    -0.73
    POSITIVE LOGITS
     remain
    1.43
     remains
    1.41
     Remain
    1.29
     Remains
    1.28
    remain
    1.20
    remains
    1.19
     remained
    1.11
    Remain
    1.10
    mains
    1.01
     demeure
    0.99
    Activations Density 0.074%

    No Known Activations