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. 1-GEMMASCOPE-RES-16K
    6. 6951
    Prev
    Next
    INDEX
    Explanations

    the color blue, particularly 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 @ 1-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.1.hook_resid_post
    Hook Layer
    1
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Roskov
    -1.22
    tanleria
    -1.06
    Personendaten
    -0.96
     ainfi
    -0.85
    HtmlAttribute
    -0.84
     Majefty
    -0.82
    AddTagHelper
    -0.80
     plufieurs
    -0.80
     nonUne
    -0.79
     vectorielles
    -0.79
    POSITIVE LOGITS
     Blue
    2.59
    Blue
    2.33
     blue
    2.07
     BLUE
    1.99
    blue
    1.94
    BLUE
    1.82
     Blu
    1.48
    蓝
    1.46
    blu
    1.39
     blu
    1.38
    Activations Density 0.047%

    No Known Activations