© 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. 11-GEMMASCOPE-RES-16K
    11. 6435
    Prev
    Next
    INDEX
    Explanations

    references to the concept of "hard work" and related themes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Hook Layer
    11
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    adaptiveStyles
    -1.28
     Rossetti
    -1.19
    yntaxException
    -1.13
    Datuak
    -1.11
    :✨
    -1.08
    LabelTagHelper
    -1.05
    Viki
    -1.04
    Portale
    -1.02
     Ceci
    -0.99
     AssemblyVersion
    -0.98
    POSITIVE LOGITS
     HARD
    1.22
     Hard
    1.13
     hard
    1.11
    HARD
    1.08
    Hard
    1.08
    hard
    1.04
    -
    0.91
     Hardin
    0.88
    硬
    0.87
     Harding
    0.86
    Activations Density 0.038%

    No Known Activations