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. 15-GEMMASCOPE-RES-16K
    6. 2203
    Prev
    Next
    INDEX
    Explanations

    references to models in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_15/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Чу
    -0.65
    ignac
    -0.61
     Eup
    -0.60
     magnética
    -0.59
    mailto
    -0.59
    uptime
    -0.58
     bumpers
    -0.58
    achten
    -0.58
    FontAwesomeIcon
    -0.58
    PriorityQueue
    -0.57
    POSITIVE LOGITS
     MODEL
    1.60
     models
    1.54
     Model
    1.50
     model
    1.47
     Models
    1.42
    Models
    1.39
    model
    1.37
    MODEL
    1.36
     ModelExpression
    1.32
    models
    1.29
    Activations Density 0.087%

    No Known Activations