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. 19-GEMMASCOPE-RES-16K
    6. 11963
    Prev
    Next
    INDEX
    Explanations

    references to individuals named Chris or related variations of that name

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 19-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_19/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Hook Layer
    19
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     general
    -0.48
     General
    -0.45
     kaynağından
    -0.44
    IBOutlet
    -0.44
    penup
    -0.43
     Löwen
    -0.43
    GENERAL
    -0.43
     rangs
    -0.43
    ھے
    -0.43
    ва
    -0.43
    POSITIVE LOGITS
    CHRIS
    0.95
     CHRIS
    0.87
     Chris
    0.86
    Chris
    0.83
     Chri
    0.81
     chris
    0.80
    opher
    0.78
     Christie
    0.76
     Chriſt
    0.76
    aarrggbb
    0.76
    Activations Density 0.059%

    No Known Activations