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. 58363
    Prev
    Next
    INDEX
    Explanations

    terms related to the evaluation of firms and their relationships with clients

    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
     EconPapers
    -0.73
    IVEREF
    -0.57
    EndContext
    -0.55
    rsiniz
    -0.53
     meridional
    -0.52
     Meksiku
    -0.50
    WillAppear
    -0.50
     unplayable
    -0.50
    prüche
    -0.49
    MessageTagHelper
    -0.48
    POSITIVE LOGITS
    AnimationsModule
    0.71
     reputable
    0.61
     adequate
    0.59
    TabIndex
    0.56
     adequately
    0.53
     company
    0.52
     quality
    0.51
     validate
    0.50
     properly
    0.49
     نباش
    0.48
    Activations Density 0.038%

    No Known Activations