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. 15024
    Prev
    Next
    INDEX
    Explanations

    occurrences of the definite article "l'" in French

    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
     Efq
    -0.89
     Theſe
    -0.87
     Houſe
    -0.81
     ſeveral
    -0.79
    ſelf
    -0.74
     Monfieur
    -0.71
     iſt
    -0.69
     himſelf
    -0.69
     Chrif
    -0.68
     pleaſure
    -0.68
    POSITIVE LOGITS
     l
    1.90
     I
    0.75
     '\\;'
    0.68
    utilisons
    0.65
    sl
    0.64
    ngOnInit
    0.64
     NSCoder
    0.63
    PerformLayout
    0.62
     betweenstory
    0.62
    verwijspagina
    0.62
    Activations Density 0.078%

    No Known Activations