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. 12-GEMMASCOPE-RES-16K
    6. 4988
    Prev
    Next
    INDEX
    Explanations

    entities and businesses in technology and media contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     виправивши
    -0.61
    Parcelize
    -0.60
     CreateTagHelper
    -0.57
     autorytatywna
    -0.57
    PerformLayout
    -0.57
     betweenstory
    -0.56
    numerusform
    -0.55
    Leaving
    -0.54
    omitempty
    -0.54
     doPost
    -0.53
    POSITIVE LOGITS
    министра
    0.54
    énieurs
    0.53
    ubwa
    0.51
     officials
    0.47
    wegen
    0.46
     payment
    0.46
    }],
    
    0.46
    bbia
    0.46
     pihak
    0.45
     ทาง
    0.45
    Activations Density 0.505%

    No Known Activations