© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 7-GEMMASCOPE-RES-16K
    11. 14497
    Prev
    Next
    INDEX
    Explanations

    references to various models in scientific analysis or research

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 7-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_7/width_16k/average_l0_69
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Hook Layer
    7
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    achten
    -0.68
    doPost
    -0.67
    IBarButtonItem
    -0.66
    FontAwesomeIcon
    -0.65
    WebVitals
    -0.65
     Ngh
    -0.65
     Kear
    -0.65
    Чу
    -0.63
    uptime
    -0.63
     sopr
    -0.63
    POSITIVE LOGITS
     model
    2.02
     MODEL
    1.97
     models
    1.96
     Model
    1.91
     Models
    1.77
    model
    1.76
    MODEL
    1.72
    Models
    1.63
    Model
    1.61
     MODELS
    1.60
    Activations Density 0.087%

    No Known Activations