Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 25-GEMMASCOPE-RES-16K
    6. 8716
    Prev
    Next
    INDEX
    Explanations

    terms related to project management and development environments

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.hook_resid_post
    Hook Layer
    25
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    XmlAccessorType
    -0.57
    tableFuture
    -0.57
    gorm
    -0.53
     Foro
    -0.53
    Cursors
    -0.53
    labelledby
    -0.53
     borer
    -0.52
    InputBorder
    -0.52
    ErrorListener
    -0.50
    ácara
    -0.49
    POSITIVE LOGITS
     deploy
    1.07
     deployment
    1.06
    deploy
    0.96
     Deploy
    0.95
    Deploy
    0.95
     publish
    0.95
     deploying
    0.94
     production
    0.93
     Deployment
    0.93
     deployments
    0.91
    Activations Density 0.766%

    No Known Activations