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. 2-GEMMASCOPE-RES-16K
    6. 6641
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "only"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     維
    -0.61
     criado
    -0.55
    MetaObject
    -0.54
    ViewFeatures
    -0.49
     doPost
    -0.49
     TokenType
    -0.48
    stuk
    -0.47
    kwds
    -0.47
     vítima
    -0.47
    tired
    -0.47
    POSITIVE LOGITS
     فريبيس
    0.87
     Only
    0.83
    脚注の使い方
    0.83
    Only
    0.83
    StructEnd
    0.82
    MethodManager
    0.74
     GenerationType
    0.72
    ONLY
    0.71
     Seulement
    0.70
     Exacts
    0.68
    Activations Density 0.193%

    No Known Activations