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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 65k
    5. 0-GEMMASCOPE-RES-65K
    6. 9711
    Prev
    Next
    INDEX
    Explanations

    mentions of the term "mel" and its variations, suggesting a focus on media or entertainment contexts, particularly related to "Fox" news programs and themes of pursuit

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 0-gemmascope-res-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_0/width_65k/average_l0_73
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    Data Type
    float32
    Hook Name
    blocks.0.hook_resid_post
    Hook Layer
    0
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     habet
    -0.89
    CppMethod
    -0.82
    Хьажоргаш
    -0.79
    SerializedSize
    -0.79
     Waray
    -0.78
     titolata
    -0.73
     provisoire
    -0.71
    SourceChecksum
    -0.71
     كومونز
    -0.69
     défaite
    -0.69
    POSITIVE LOGITS
     Fox
    0.65
    oir
    0.60
    hild
    0.58
    Fox
    0.57
    Potato
    0.56
     FOX
    0.54
    bumptech
    0.54
     fox
    0.54
    FOX
    0.54
     Tsai
    0.51
    Activations Density 0.026%

    No Known Activations