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 - 16k
    5. 12-GEMMASCOPE-RES-16K
    6. 10155
    Prev
    Next
    INDEX
    Explanations

    specific mentions of cookies and privacy practices related to website usage

    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
     ContentValues
    -0.61
     (
    -0.48
    waża
    -0.48
    chartInstance
    -0.47
    bindParam
    -0.46
     
    -0.46
     spo
    -0.46
    msgTypes
    -0.46
     JsonConvert
    -0.45
    SourceChecksum
    -0.45
    POSITIVE LOGITS
     itſelf
    0.85
    }))
    
    0.73
     pleaſure
    0.72
    ſelf
    0.69
     ―――――
    0.67
    ſelves
    0.67
    ptid
    0.66
    AutoScaleMode
    0.66
     Eſ
    0.66
     iſt
    0.65
    Activations Density 0.090%

    No Known Activations