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 - 65k
    5. 12-GEMMASCOPE-RES-65K
    6. 13569
    Prev
    Next
    INDEX
    Explanations

    references to pH values and related acidity information

    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-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_12/width_65k/average_l0_72
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    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
     Worthington
    -0.64
    WriteLiteral
    -0.63
     AppBundle
    -0.61
    پیوند
    -0.58
    getOutputStream
    -0.57
     Arias
    -0.57
    有的
    -0.57
     occidentalis
    -0.57
    Kilder
    -0.56
    
    -0.56
    POSITIVE LOGITS
     pH
    1.71
    pH
    1.59
     pinulongan
    1.02
     temperatuur
    0.88
    rrggbb
    0.87
     acidosis
    0.81
     Bohr
    0.80
    sidemargin
    0.78
    SequentialGroup
    0.78
     Phaser
    0.76
    Activations Density 0.017%

    No Known Activations