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. 20-GEMMASCOPE-RES-16K
    6. 13617
    Prev
    Next
    INDEX
    Explanations

    text related to software and programming, particularly in database management and analysis tools

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    TestingModule
    -0.59
    APIView
    -0.54
     pulumi
    -0.53
    SourceChecksum
    -0.52
    mapbox
    -0.51
     ExecuteAsync
    -0.50
    shub
    -0.50
     MonoBehaviour
    -0.50
    parseFrom
    -0.49
     Réponses
    -0.49
    POSITIVE LOGITS
     software
    1.02
     logiciel
    0.83
    software
    0.82
     licenses
    0.79
     license
    0.79
     Software
    0.78
     licencia
    0.76
    軟體
    0.74
    软件
    0.73
     logiciels
    0.72
    Activations Density 0.411%

    No Known Activations